<h2 dir="ltr" id="isPasted">Event Overview</h2><p dir="ltr">Hackster's Impact Summit is a free two-day virtual event (14th-15th November, 2023) dedicated to inspiring developers, connecting organizations, and accelerating technological innovation. This year's topic examines how to build resilient and sustainable cities.&nbsp;</p><h2 dir="ltr">Who Should Attend</h2><p dir="ltr">The Impact Summit is inviting technologists, engineers, community trailblazers and technology providers. The event offers an opportunity to examine the transformative role of machine learning, advanced data analytics, and IoT in enhancing the management and maintenance of urban infrastructure, public services, and critical facilities.</p><h2 dir="ltr">Session Highlights</h2><p dir="ltr"><strong>Day 1</strong> commences with Kate Kallot, CEO of Amini, examining the harmony of socioeconomic growth with environmental conservation. Followed by a workshop on predictive maintenance using Nordic Thingy:53, led by David Tischler from Edge Impulse. The day progresses with a demo on SCADA system modernization with Bryan Costanich, Wilderness Labs CEO, and concludes with a panel discussion on urban environment innovation and several workshops.</p><p dir="ltr"><strong>Day 2</strong> opens with a keynote from Tomas Diez, Executive Director of Fab City Foundation, discussing community-driven sustainable urban development. The day continues with a panel on technology resiliency, workshops on sustainable city AI and embedded programming, and concludes with a demo on frugal innovation for urban development by Kevin Schmidt from UNDP.</p><p dir="ltr"><a href="https://wevlv.co/impactsummit2023" target="_blank" rel="noopener noreferrer" class="button-main-action">Learn more now</a></p><h2 dir="ltr">Insights</h2><p dir="ltr">The summit features speakers from leading organizations and companies who are at the forefront of urban technology and development. They will share real-world applications and insights into the impact of technological innovation on city living.</p><h3 dir="ltr">Technical Deep Dive</h3><p dir="ltr">Attendees will benefit from a practical approach to smart city challenges, with in-depth technical workshops on IoT, AI at the edge, and predictive maintenance. These sessions will equip participants with knowledge applicable to real-world urban systems.</p><h3 dir="ltr">Interactive Engagement</h3><p dir="ltr">Live panel discussions provide a platform for interactive dialogue between technology experts, policymakers, and attendees, focusing on the translation of ideas into tangible urban solutions.</p><h3 dir="ltr">Learning Outcomes</h3><p dir="ltr">Participants will leave with actionable strategies for deploying technology in urban infrastructure, insights into sustainable development practices, and a comprehensive understanding of the predictive maintenance landscape.</p><h3 dir="ltr">Event Accessibility</h3><p dir="ltr">Sessions are scheduled in Central Time (CST).</p><p dir="ltr">Post-event access to session recordings will be provided to all registrants.</p><p dir="ltr"><a href="https://wevlv.co/impact-summit-zoom" target="_blank" rel="noopener noreferrer" class="button-main-action">Register now</a></p><p dir="ltr">Would you like to learn more about the Impact Summit? <a href="https://wevlv.co/impactsummit2023" target="_blank" rel="noopener noreferrer">Visit this page.</a></p>

Accelerating Urban Efficiency through Technology. Explore How AI & IoT Drive the Future of Sustainable Urban Living



Impact Summit 2023 Virtual Event

<p dir="ltr" id="isPasted">In engineering, quality control ensures the reliability, safety, and consistency of products and processes. As industries evolve, the demand for continual improvement becomes paramount, not just to stay competitive but also to guarantee the highest standards of safety and reliability. In this dynamic landscape, the introduction of Edge AI emerges as a transformative solution, poised to revolutionize quality control mechanisms.</p><p dir="ltr">Quality control, especially in engineering environments, is not just about maintaining standards; it's about elevating them. The competitive nature of today's industries necessitates a relentless pursuit of perfection. Traditional methods, while effective, often need more agility and real-time responsiveness than modern manufacturing and production environments require. This is where the need for continual improvement and innovation comes into play.</p><p dir="ltr">Edge AI, a technology that emphasizes processing data at its origin rather than relying on a centralized data center, presents a sophisticated advancement in quality control. By integrating AI capabilities directly into devices and systems on the manufacturing floor, Edge AI facilitates real-time analysis, immediate feedback, and rapid decision-making. Such capabilities are not just enhancements; they are transformational, enabling businesses to detect anomalies, predict issues, and ensure optimal quality at unprecedented speeds.</p><p dir="ltr">Drawing insights from various industry studies and advancements, it's evident that Edge AI's integration into quality control processes offers a promising avenue for industries to stay ahead, ensuring both competitiveness and unparalleled quality standards.</p><p dir="ltr">Let's delve deeper!</p><p dir="ltr"><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p><h2 dir="ltr">The Imperative of Quality Control in Engineering</h2><p dir="ltr">Quality control has traditionally been a reactive process, heavily reliant on post-production inspections and tests. Traditional methods, while foundational, have their limitations:</p><p dir="ltr">Traditional Quality Control Systems: Historically, quality assurance has been downstream-focused, emphasizing production and testing. This approach, often characterized by repetitive design-prototype-test cycles, can be likened to a trial-and-error method. Such methods might only sometimes yield optimal designs, leading to increased costs, extended cycle times, and potential compromises in customer quality.&nbsp;</p><p dir="ltr">The traditional system operates on the premise that as long as a product is within specification limits, it meets customer requirements. However, the business implications of a product being "barely within specification limits" and "right on target" are vastly different.</p><p dir="ltr">Financial and Operational Implications: Inadequate quality control can have severe financial repercussions. Products that don't meet quality standards can lead to recalls, warranty claims, and loss of customer trust. Operationally, inadequate quality control can result in increased wastage, rework, and delays in production schedules.</p><p dir="ltr">Evolving Standards and Expectations: With the rapid advancements in technology and globalization, industry standards are continually evolving. Customers today are more informed and have higher expectations. They demand products that are functional but also safe, durable, and innovative. This drives the need for more robust and proactive quality control processes.</p><p dir="ltr">The limitations of traditional quality control methods and the changing landscape of customer expectations underscore the need for innovative solutions. As industries strive for perfection, there's a pressing demand for methods that are reactive but also proactive, predictive, and efficient.</p><h2 dir="ltr">The Advent of Edge AI in Quality Control</h2><p dir="ltr">As traditional methods have inherent limitations, the industry is turning to innovative solutions such as Edge AI.</p><p dir="ltr">Edge AI refers to deploying artificial intelligence algorithms directly on the devices where data is generated rather than processing this data in a centralized cloud-based system. This proximity to the data source facilitates real-time data processing, ensuring swift responses and immediate insights.</p><h3 dir="ltr">Addressing Traditional Limitations</h3><p dir="ltr">Traditional quality control methods, while foundational, often lag in real-time responsiveness and agility. Edge AI, with its on-device processing capabilities, addresses these gaps. By analyzing data at the source, it eliminates the latency associated with transmitting data to a central server for processing. This not only speeds up the quality control process but also enhances its accuracy and efficiency.</p><h3 dir="ltr">Benefits of Edge AI in Quality Control</h3><p dir="ltr">Real-time Anomaly Detection: With Edge AI, anomalies in the manufacturing or production process can be detected in real-time, allowing immediate corrective actions.</p><p dir="ltr">Predictive Maintenance: Edge AI can predict equipment failures before they occur, ensuring uninterrupted operations and reducing downtime.</p><p dir="ltr">Reduced Operational Costs: By processing data locally, Edge AI reduces the need for data transmission and cloud storage, leading to potentially significant cost savings. Additionally, the efficiency gains from real-time insights and predictive maintenance further contribute to operational cost reductions.</p><p dir="ltr">Integrating Edge AI into quality control processes signifies a monumental shift from reactive to proactive quality assurance. As industries continue to evolve, technologies like Edge AI will play a pivotal role in ensuring that quality remains at the forefront of all operations.</p><h2 dir="ltr">Spotlight on Edge Impulse</h2><p dir="ltr">In the rapidly evolving domain of Edge AI, Edge Impulse stands out as a pioneering platform, offering a comprehensive suite of tools and capabilities tailored for deploying machine learning models on edge devices.</p><p dir="ltr">Edge Impulse is a cutting-edge platform designed to simplify creating and deploying AI models on edge devices. By providing a user-friendly interface, Edge Impulse allows engineers and developers to harness the power of AI without the complexities often associated with traditional machine learning workflows. One of the standout features of Edge Impulse is its ability to streamline the deployment of machine learning models directly on edge devices.&nbsp;</p><h3 dir="ltr">Key Features of Edge Impulse</h3><p dir="ltr">Data Collection: Edge Impulse Studio offers a data acquisition tool that allows users to upload datasets, facilitating the training and validation of machine learning models.</p><p dir="ltr">Model Training: The platform provides various tools and algorithms, including the YOLOv5 object detection model, which can be optimized for resource-constrained devices.</p><p dir="ltr">Deployment: After training, Edge Impulse facilitates the deployment of the model on edge devices, such as the <a href="https://www.renesas.com/us/en/products/microcontrollers-microprocessors/rz-mpus/rzv2l-evkit-smarc-som-evaluation-kit-rzv2l-mpu-ai-accelerator" target="_blank">Renesas RZ/V2L Evaluation Board</a>, ensuring seamless integration and real-time performance.</p><p dir="ltr">Edge Impulse's capabilities extend beyond just quality control in manufacturing. Its versatile platform can be adapted to various applications, making it a valuable tool for industries aiming to leverage the benefits of Edge AI.</p><h2 dir="ltr">Edge Impulse in Action: A Case Study</h2><p dir="ltr">Quality inspections are pivotal in ascertaining that products meet the required standards and specifications. A case study involving Edge Impulse offers a deep dive into how cutting-edge technology can elevate these inspections, ensuring optimal product quality.</p><p dir="ltr">The Challenge: Manufacturers often grapple with establishing a comprehensive inspection procedure encompassing all facets of a product's quality. Traditional methods, while effective, may only sometimes offer the agility and real-time responsiveness required in modern manufacturing environments. The challenge lies in seamlessly integrating the inspection process into the existing workflow without causing disruptions, all while maintaining consistent quality across batches.</p><p dir="ltr">The Edge Impulse Solution: Solomon Githu, an engineer, envisioned a <a href="https://www.hackster.io/sologithu/product-inspection-with-renesas-rz-v2l-and-edge-impulse-cf0700" target="_blank">solution</a> that would seamlessly integrate into existing processes and autonomously discern product quality. He conceptualized an inspection device employing computer vision and machine learning to inspect products as they traverse an assembly line swiftly.&nbsp;</p><p dir="ltr">The objective was clear: the device should autonomously determine product quality in milliseconds.</p><p dir="ltr">To bring this vision to life, Githu leveraged the <a href="https://edgeimpulse.com/product" target="_blank">Edge Impulse Studio</a>. The platform's web-based interface replaced the complexities of traditional machine learning with a user-friendly, point-and-click experience. Using an object detection algorithm, the system was trained to inspect products and discern their quality rapidly. The training involved a dataset comprising both high-quality products and those with defects.</p><p dir="ltr">To ensure real-time responsiveness, Githu employed the <a href="https://www.renesas.com/us/en/products/microcontrollers-microprocessors/rz-mpus/rzv2l-evkit-smarc-som-evaluation-kit-rzv2l-mpu-ai-accelerator" target="_blank">Renesas RZ/V2L Evaluation Board</a>, specifically designed for computer vision and machine learning applications. Paired with a <a href="https://coral.ai/products/camera/" target="_blank">Google Coral camera</a>, the system was equipped to inspect products and make real-time determinations visually.</p><p dir="ltr">Outcomes: The system was tested using a custom-built miniature conveyor belt, with printed images of products (in this case, submersible pump impellers) moving along it. The camera, positioned above, relayed real-time visuals to a custom web application, which then displayed the products and maintained a count of the good and defective items it detected. The results were compelling: the system showcased high accuracy, aligning with the impressive performance metrics observed during model training and testing.</p><p dir="ltr">Conclusion: This case study underscores the transformative potential of Edge Impulse in the realm of quality control. By harnessing the power of Edge AI, manufacturers can elevate their quality inspection processes, ensuring that products not only meet but exceed the desired quality standards.</p><h2 dir="ltr">The Road Ahead</h2><p dir="ltr">Integrating Edge AI into quality control processes has showcased transformative results in various engineering domains. As industries continue to evolve and the demand for real-time, efficient, and accurate quality control mechanisms grows, the potential for further integration of Edge AI becomes even more pronounced.</p><p dir="ltr"><strong>Potential Across Engineering Domains:&nbsp;</strong>While the manufacturing sector has been an early adopter of Edge AI for quality control, other engineering domains, such as civil engineering, electronics, and aerospace, could benefit immensely from this technology. The ability to process data in real-time at the source can lead to enhanced structural integrity checks, real-time monitoring of electronic components, and swift anomaly detection in aerospace systems.</p><p dir="ltr"><strong>Scalability and Adaptability of Edge Impulse:</strong> Platforms like Edge Impulse are designed with scalability and adaptability in mind. Whether adapting to different data types, integrating with various edge devices, or scaling to handle vast amounts of data, Edge Impulse ensures that diverse quality control requirements across industries are met precisely. The platform's capabilities, such as data collection, model training, and deployment, can be tailored to suit specific industry needs, making it a versatile tool for quality control.</p><p dir="ltr"><strong>Meeting Diverse Quality Control Requirements:</strong> As industries diversify and products become more complex, the quality control requirements also evolve. Edge AI platforms, with their adaptability, can cater to these diverse needs, ensuring that quality control is not just about meeting standards but setting new benchmarks.</p><h2 dir="ltr">Conclusion</h2><p dir="ltr">Integrating Edge AI into quality control processes signifies a significant stride in the engineering domain. Platforms like Edge Impulse have showcased the capability to enhance these processes, offering real-time data processing and decision-making at the source. Such advancements are not just about improving efficiency but also about ensuring consistent and high-quality outputs.</p><p dir="ltr">Edge Impulse, in particular, has demonstrated its prowess in facilitating the deployment of machine learning models on edge devices. It is a valuable tool for industries aiming to improve quality control mechanisms. Its capabilities, ranging from data collection to model training and deployment, are tailored to meet the specific needs of various industries, ensuring adaptability and scalability.</p><p dir="ltr">For engineering firms, the message is clear: the future of quality control lies in harnessing the power of Edge AI. By exploring and adopting solutions like Edge Impulse, firms can position themselves at the forefront of technological advancements, ensuring they meet the evolving standards of quality and efficiency in the industry.</p><p dir="ltr"><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p><h2 dir="ltr">References</h2><ol><li dir="ltr"><p dir="ltr"><a href="https://metrology.news/re-imagining-manufacturing-quality-with-ai-and-edge-computing/" target="_blank">Re-imagining Manufacturing Quality with AI and Edge Computing</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://edgeimpulse.com/blog/elevating-quality-standards-with-ai" target="_blank">Elevating Quality Standards with AI</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://www.griddynamics.com/events/quality-control-manufacturing-webinar-q3-2022" target="_blank">Quality 4.0: Reimagining AI and Quality Control Automation for Smart Manufacturing</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://developer.ibm.com/articles/enabling-distributed-ai-with-edge-computing/" target="_blank">Enabling Distributed AI for Quality Inspection in Manufacturing with Edge Computing</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://edgeimpulse.com/blog/elevating-quality-standards-with-ai" target="_blank">https://edgeimpulse.com/blog/elevating-quality-standards-with-ai</a></p></li></ol>

Revolutionizing Engineering Quality Control: The Transformative Power of Edge AI

Edge AI: A Paradigm Shift in Quality Control

<p dir="ltr" id="isPasted">For those eager to grasp the intricacies of AI and neuromorphic computing BrainChip's podcast series stands out as a strong source of knowledge. In their 28th episode titled "This Is Our Mission," BrainChip's Rob Telson orchestrates a riveting conversation with Tenstorrent's COO, Keith Witek, and BrainChip's CMO, Nandan Nayampally. This episode provides a treasure trove of insights, making it a must-listen for engineers working in the industry or warning to know more about the cutting edge of computing.</p><h2 dir="ltr">About the Guests</h2><p dir="ltr">Rob Telson, the Vice President of Ecosystem and Partnerships at BrainChip, is the dynamic force behind the podcast series. With a keen eye for curating meaningful discussions, Telson ensures that each episode is both enlightening and engaging. His role at BrainChip involves fostering partnerships and building a robust ecosystem, making him the perfect host to bridge the gap between technical intricacies and their real-world implications.&nbsp;</p><p dir="ltr">Keith Witek, the COO of Tenstorrent, boasts an impressive resume. With degrees spanning Business, Computing, Electrical Engineering, and Law, Witek has left his mark at tech giants like Google and Tesla. His expertise in strategic alliances, especially in consumer electronics, sets the stage for a profound discussion.</p><p dir="ltr">Nandan Nayampally, BrainChip's CMO, brings to the table a rich history in the semiconductor domain. With stints at AMD, Denali Software, and even Amazon's Alexa, Nayampally's insights into computing trends are invaluable.</p><h2 dir="ltr">Podcast Key Discussion Points</h2><p dir="ltr">AI's Staying Power: The realm of technology is no stranger to fleeting trends, but AI is not one of them. As discussed in the podcast, AI has firmly established itself as a transformative force, with its applications and implications reaching far and wide. The consensus between the experts is clear: AI's influence in shaping the future is undeniable, and its role in various sectors is only set to grow.</p><p dir="ltr"><strong>Real-world AI Impacts:</strong> The podcast delves into tangible ways AI is making a difference in our lives. From the significant reduction in car-related fatalities due to AI-driven safety features to the potential of personalized healthcare solutions tailored to individual needs, AI's footprint in real-world scenarios is expanding rapidly.</p><p dir="ltr"><strong>Challenges in AI Scalability:</strong> Despite its vast potential, AI faces its set of challenges. The podcast highlights issues like the massive influx of data that systems need to process and the impending slowdown of Moore’s Law. These challenges pose questions about the scalability and efficiency of current AI models.</p><p dir="ltr"><strong>Innovative Solutions:&nbsp;</strong>The conversation takes an optimistic turn when discussing the solutions. Industry leaders, including BrainChip and Tenstorrent, are at the forefront of addressing these challenges. Their innovative approaches and technologies promise to overcome existing barriers, paving the way for a more AI-integrated future.</p><p dir="ltr"><strong>Promising Tech Deployment Models:</strong> The podcast also touches upon the future of technology deployment. The concept of chiplets, for instance, offers a glimpse into the potential shifts in how we might approach hardware design and integration in the coming years, ensuring more efficient and scalable AI implementations.</p><h2 dir="ltr">Closing Thoughts</h2><p dir="ltr">This podcast episode is a great resource for anyone interested in the future of AI, regardless of their background or level of knowledge. It promises to offer insights into real-world applications, challenges, and solutions that are shaping the evolution of AI. As the world stands at the brink of an AI revolution, it becomes increasingly important to understand its nuances and potential implications.</p><p dir="ltr"><a href="https://www.wevolver.com/profile/brainchip" target="_blank" rel="noopener noreferrer">Read more about BrainChip on Wevolver. </a></p>

Navigating AI's Future in a Riveting Podcast Discussion

BrainChip's Deep Dive into AI's Future: A Podcast with Tenstorrent's COO Keith Witek

<p>The winners of the <a href="https://www.tinyml.org/event/tinyml-hackathon-2023-pedestrian-detection/" target="_blank" rel="noopener noreferrer">Pedestrian Safety Challenge Hackathon</a> competition have been announced. The hackathon was a collaboration between the TinyML Foundation the City of San Jose and &nbsp;Sony Semiconductor Solutions America (SSSA). This initiative began in May with the aim of reducing pedestrian-involved accidents, aligning with the city's Vision Zero initiatives.&nbsp;</p><p>The challenge was a response to the increasing number of pedestrian injuries and fatalities due to issues such as distracted driving, distracted walking, and illegal road crossings.</p><p><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe width="640" height="360" src="https://www.youtube.com/embed/ZhBCtfalcOk?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"><span class="fr-mk" style="display: none;">&nbsp;</span></iframe></span></p><p dir="ltr">The competition saw participation from 29 teams globally, including countries like the United States, Germany, Lebanon, Nigeria, and Saudi Arabia. Teams from Silicon Valley and the San Francisco Bay Area also took part. Mark Hanson, Vice President and Head of Marketing for System Solution Business Development at SSSA, expressed his optimism about the innovative solutions presented by the teams and their potential to benefit communities worldwide.</p><p>The<a href="https://leopardimaging.com/" target="_blank" rel="noopener noreferrer"> Leopard Imaging </a>team clinched the first place with their solution that utilized SSSA's AiTrios™ platform and IMX500-enabled hardware. The Neurohm team secured the second place, followed by the team from King Abdullah University of Science and Technology (KAUST) in third place. The KAUST team also received a special Edge Impulse award.</p><p>Leopard Imaging is a global leader in camera design and manufacture, creating state-of-the-art, AI-based cameras for Fortune 500 companies. Their reputation is credited by excellent camera manufacture and camera tuning by experts of the field, and the use of highly precise Active Alignment (AA) machines. Over the years their excellence in building artificially intelligent and robust camera solutions has earned Leopard Imaging many certifications like those for automotive-grade camera manufacture and aviation-grade camera development. Their cameras have spanned all imaginable industries, from autonomous vehicles to cashierless carts, smart street lights, and embedded cameras in drones.</p><p>Read more about the hackathon in our previous article <a href="https://www.wevolver.com/article/revolutionizing-traffic-safety-the-global-tinyml-traffic-hackathon" target="_blank" rel="noopener noreferrer">here</a>.&nbsp;</p>

 Leopard Imaging wins global challenge. 

Winners of the tinyML Traffic Hackathon demonstrate the future of pedestrian safety

<p dir="ltr" id="isPasted">Moore’s Law and distributed cloud computing have enabled artificial intelligence (AI) and machine learning (ML) applications to effectively overcome Von Neumann bottlenecks that once limited data throughput on conventional systems. With enormous amounts of targeted compute power and memory available in the cloud, AI/ML training and inference models continue to increase in both size and sophistication.</p><p dir="ltr">However, cloud-based data centers have created a new set of challenges for AI applications at the edge such as latency, power, and security. Untethering edge AI from the cloud helps address some of these issues—and creates opportunities for the semiconductor industry to design new products with smarter and more independent sensors, devices, and systems.</p><p dir="ltr">For example, autonomous vehicles leverage cloud-free, edge AI learning at high speeds to continuously update and define safety parameters that make it easier for onboard systems to detect anomalous structural vibrations and engine sounds.</p><p dir="ltr">Cloud-free edge AI also enables gesture control with faster response times, allowing doctors and therapists to help people with disabilities interact with sophisticated robotic assistance devices. In the future, field hospitals in disaster zones can deploy medical robots with advanced edge AI capabilities, even if connectivity is limited.</p><p dir="ltr">Lastly, smart farms in remote areas depend on cloud-free AI to help lower food prices by efficiently increasing crop yields with intelligent soil sensors, irrigation systems, and autonomous drones.</p><h2 dir="ltr">The human brain shows us the way</h2><p dir="ltr">Untethering edge AI from the cloud is an important first step to enabling smarter endpoints. However, the semiconductor industry must also acknowledge the inefficiencies of simply scaling down AI hardware at the edge. Indeed, advanced edge applications are already hitting the limits of conventional AI silicon and standard learning models.</p><p dir="ltr">Many chips used in edge applications today are still general-purpose processors such as GPUs that consume approximately 1,000X more power than purpose-built edge silicon. Although some smart devices are equipped with low-power digital signal processors (DSPs), these single-purpose chips typically lack advanced learning and analytics capabilities.</p><p dir="ltr">In recent years, neuromorphic computing has unlocked more efficient architectures and learning models such as incremental and one-shot learning for edge AI. Smart edge silicon that follows the principles of essential AI—doing more with less—now supports a new generation of advanced multimodal and autonomous use cases with independent learning and inference capabilities, faster response times, and a lower power budget.</p><p dir="ltr">These include self-driving cars that personalize cabin settings for individual drivers, automated factories and warehouses, advanced speech and facial recognition applications, and robots that use sophisticated sensors to see, hear, smell, touch, and taste.&nbsp;</p><h2 dir="ltr">The future’s not only bright, it’s essential</h2><p dir="ltr">Edge AI presents both a challenge and opportunity for the semiconductor industry to look well beyond cutting the cord to the cloud and simply scaling down conventional chip architectures. Neuromorphic edge AI silicon is already enabling people to seamlessly interact with smarter devices that independently learn new skills, intelligently anticipate requests, and instantly deliver services.</p><p dir="ltr">Specific strategies to unlocking the full potential of edge AI will undoubtedly vary, which is why it is important to explore a future in which semiconductor companies play a collaborative role in helping to design and implement new neuromorphic architectures.</p><h2 dir="ltr">Edge AI: The Cloud-Free Future is Now Whitepaper</h2><p dir="ltr">Brainchip and the Global Semiconductor Alliance (GSA) have jointly published a white paper titled “Edge AI: The Cloud-Free Future is Now” that discusses:</p><ul><li dir="ltr"><p dir="ltr">Untethering edge AI from the cloud</p></li><li dir="ltr"><p dir="ltr">Overcoming the limits of conventional AI silicon and learning methodologies</p></li><li dir="ltr"><p dir="ltr">Unlocking new architectures and learning models with neuromorphic computing</p></li><li dir="ltr"><p dir="ltr">Supporting autonomous edge AI applications</p></li></ul><p dir="ltr">“We are excited to support the publication of this white paper as it is a call to our industry to work together to address the unique learning and performance requirements of edge AI,” said Brainchip Marketing and Strategy Advisor, Jerome Nadel. “We hope it provokes conversation and collaboration—and ultimately enables effective edge compute to be universally deployable across real world applications such as connected cars, consumer electronics, and industrial IoT.”</p><p dir="ltr"><a href="https://brainchip.com/#whitepaper" target="_blank" rel="noopener noreferrer" class="button-main-action">Click here to read the full white paper.</a></p><h2 dir="ltr">Building collective knowledge</h2><p dir="ltr">Over the next few months, as part of our new series spotlighting Neuromorphic computing, we will share content that explores how neuromorphic edge silicon can mimic the human brain to analyze only essential sensor inputs at the point of acquisition. Specifically, we’ll take a closer look at the four primary design principles of neuromorphic edge silicon, how to efficiently scale and optimize on-chip memory, as well as strategies for leveraging inference and one-shot learning. We’ll also discuss real-world edge AI use cases, including automotive edge learning at high speeds, wine tasting, object detection and classification, and keyword spotting.</p><p dir="ltr">Follow the <a href="https://www.wevolver.com/profile/brainchip" target="_blank" rel="noopener noreferrer">BrainChip</a> Wevolver profile to stay-up-to date.&nbsp;</p>

This is the first article in a new series from BrainChip highlighting their vision and technology. 


Edge AI: Why the cloud-free future is now

<p dir="ltr" id="isPasted"><em>In a recent episode of the <a href="https://www.youtube.com/@BrainChipInc" target="_blank">BrainChip podcas</a>t, Rob Telson, the Vice President of Sales and Marketing at BrainChip, spoke to Michael Azoff, an industry analyst with a focus on AI at the edge. He has 18 years of experience as an analyst and has previously worked hands-on with neural networks. We highlight some of the key discussion points below but encourage you to listen to the </em><a href="https://www.youtube.com/watch?v=xsIWZXlin7I&ab_channel=BrainChipInc" target="_blank"><em>whole episode here.</em></a></p><h2 dir="ltr">A Dive into the Past and Present</h2><p dir="ltr">During the podcast, Azoff recounted his extensive experience with AI, which began in the 1990s. He reminisced about the early days of neuromorphic computing and how it was just taking root. As the conversation progressed, he highlighted the significant milestones, emphasizing the advancements in training neuromorphic architecture-based neural networks. He also acknowledged BrainChip's notable ascent in recent years, pointing to it as evidence of the growing momentum in the neuromorphic field.</p><h3>Neuromorphic's Niche in Edge AI</h3><p dir="ltr">Azoff's recent contributions to Gigaom's reports have centered on Edge AI, a field that emphasizes inferencing at the edge. In his analysis, the Edge AI domain bifurcates into three distinct categories: ultra-low power, low power, and automotive. Intriguingly, neuromorphic architectures have carved a niche for themselves in the ultra-low power segment. Their inherent efficiency and minimal power consumption make them a natural fit for this category.</p><h3>Applications: From Surveillance to Automotive</h3><p dir="ltr">Neuromorphic architectures excel in scenarios characterized by sparse data. For instance, in visual surveillance, where a static scene is occasionally interrupted by noteworthy events, these architectures prove invaluable. Their design allows them to operate in close proximity to sensors, processing data in real-time. The applications are diverse: smart doorbells, earbuds, industrial fault detection, and even monitoring crowd density at train stations. While vision and audio remain the primary focus areas, the potential applications are vast.</p><p dir="ltr">In the automotive sector, a distinction emerges between in-cabin applications and driving functionalities. While the latter, especially autonomous driving, demands robust processing, neuromorphic computing finds its place in the former. In-cabin applications, ranging from infotainment to human-machine communication, can benefit immensely from neuromorphic's capabilities.</p><h2>Consumer Electronics: The Next Frontier</h2><p dir="ltr">As neuromorphic technology matures, its integration into consumer products is anticipated to grow. The allure of low power consumption cannot be overstated. For application developers, this presents a golden opportunity to innovate, pushing the boundaries of what's possible. In a decade, we might witness a paradigm shift where handheld devices and consumer electronics come equipped with neuromorphic processors, either as accelerators or integral components of the system's ecosystem.</p><h3>AI's Societal Impact and the Dream of Understanding the Human Brain</h3><p dir="ltr">Beyond applications, the podcast touched upon a profound topic: the beneficial impact of AI on society. AI's prowess lies in its ability to automate tasks that surpass human capabilities, especially when scale and complexity come into play. The horizon is vast, with the ultimate goal being the enhancement of AI architectures' intelligence, inching closer to the elusive general artificial intelligence.</p><p>Azoff's vision for an AI superpower is both ambitious and profound: to unravel the mysteries of the human brain. If AI can aid in understanding our brain's intricacies, the implications for neuroscience, psychology, and AI itself could be groundbreaking.</p><h3>In Conclusion</h3><p>This episode of BrainChip's podcast offers a panoramic view of neuromorphic computing's past, present, and future. As we stand on the cusp of AI's next revolution, neuromorphic computing emerges as a beacon, guiding the way forward. The journey is just beginning, and the possibilities are boundless.</p><p><a href="https://www.wevolver.com/profile/brainchip" target="_blank">&nbsp;Stay up to date with BrainChip's new content here.</a></p>

In this episode, Rob Telson speaks with Industry Expert, Michael Azoff, about neuromorphic computing in the AI space including edge AI, neural network architectures, sensory-based applications and more.

BrainChip Podcast: Exploring Neuromorphic Computing with Industry Expert Michael Azoff

<p dir="ltr" id="isPasted"><em>In a recent episode of the <a href="https://www.youtube.com/@BrainChipInc" target="_blank" rel="noopener noreferrer">BrainChip podcas</a>t, a select group of the company's top executives gathered to discuss the future trajectory of artificial intelligence (AI) and the pivotal role BrainChip is set to play in this dynamic landscape. We highlight some of the key discussion points below but encourage you to listen to the&nbsp;</em><a href="https://www.youtube.com/watch?v=zUA9Vdd6cE8&t=2s&ab_channel=BrainChipInc" target="_blank"><em>whole episode here.</em></a></p><h2 dir="ltr">Leadership with Vision</h2><p>Rob Telson Vice President, Ecosystem and Partnerships, is the driving force behind BrainChip's global outreach. With a keen understanding of market dynamics and a vision for BrainChip's expansive global presence, Tolson has been instrumental in positioning the company as a leader in the AI industry.</p><p dir="ltr">Peter Van der Made, <span lang="EN-AU">Executive Director, CTO, and Founder</span> of BrainChip, brings a wealth of experience and a visionary approach to the table. His emphasis on the importance of the company's Advanced Research Center in Perth showcases his commitment to pioneering the next wave of AI innovations. Vandermade's insights into the potential of Akida, BrainChip's flagship technology, highlight his forward-thinking approach to AI's future.</p><p>Anil Mankar, the Vice President of Product Development and also a Co-founder, offers a deep dive into the technical intricacies of BrainChip's operations. His insights into the production process, from chip manufacturing to rigorous testing, provide a glimpse into the meticulous steps BrainChip takes to ensure top-tier functionality and performance.</p><p>Lastly, Ken Scarance, the Chief Financial Officer of BrainChip, sheds light on the company's financial endeavours. His discussions on Brain Chips strategic financial initiatives, including capital raising agreements and efforts to bolster its presence in the U.S. capital markets, underscore the company's ambitions for growth and market dominance.</p><h2 dir="ltr"><strong>BrainChip's Evolution: A Glimpse into the Company's Global Strategy&nbsp;</strong></h2><p>To kick off the episode, the team outlines the company’s history, vision and future plans. BrainChip's commitment to being a global leader in the AI industry is evident in its expansive operational presence. With hubs in California, Perth, France, and India, the company has strategically positioned itself in key tech-centric locations. This global footprint not only facilitates diverse collaborations but also ensures that BrainChip remains at the pulse of AI advancements worldwide.</p><h3 dir="ltr">From Research to Production: A Strategic Pivot</h3><p dir="ltr">Historically, BrainChip has been synonymous with cutting-edge research in neuromorphic computing. Their dedication to pushing the boundaries of AI has positioned them as pioneers in the field. However, recognizing the vast commercial potential of their innovations and the industry's shifting dynamics, BrainChip is undergoing a transformation.</p><p dir="ltr">Tolson emphasised this transition in the podcast, noting the company's pivot from being primarily research-driven to adopting a production-centric approach. For engineers, this shift signifies BrainChip's intent to translate their groundbreaking research into tangible, market-ready solutions.</p><h3 dir="ltr">Engaging the Tech Community</h3><p dir="ltr">Understanding the importance of effective communication in the tech world, especially among engineers and developers, Tolson highlighted BrainChip's efforts to foster engagement. The company's podcast series, for instance, is more than just a marketing tool. It's a platform for knowledge sharing, offering insights into Brain Chips offerings, their vision for AI's future, and the technical intricacies that make their solutions stand out. Stay up to date with BrainChip activities by following their <a href="https://www.wevolver.com/profile/brainchip" target="_blank">Wevolver profile.&nbsp;</a></p><h3 dir="ltr">The Advanced Research Center: A Beacon of Innovation</h3><p dir="ltr">Located in Perth, Australia the Advanced Research Center is BrainChip's crown jewel. It's not just a research facility; it's a testament to the company's dedication to pushing the boundaries of what's possible in AI. While many in the industry focus on refining existing deep learning models, BrainChip's centre is already looking beyond, exploring the next frontier of AI innovations.</p><h3 dir="ltr">Akida: The Future of AI Technology</h3><p dir="ltr">Vandermade's enthusiasm was palpable when discussing <a href="https://brainchip.com/akida-generations/" target="_blank">Akida</a>, BrainChip's flagship technology. Akida is not just another chip in the market; it embodies BrainChip's vision for the future of AI. Two of its standout features are its low energy consumption and its on-chip learning capabilities.</p><p dir="ltr">For engineers and tech enthusiasts, these features are significant. The low energy consumption means that Akida is not only efficient but also environmentally conscious, addressing a growing concern in today's tech-driven world. On the other hand, on-chip learning capabilities represent a leap in AI technology, allowing for faster, more efficient processing without the need for constant back-and-forth with centralised data centres.</p><p dir="ltr">In Vandermade's view, Akida is set to redefine the AI industry. Its unique features position it not just as an innovative product but as a transformative solution that could shape the way we think about and implement AI in various applications.</p><p dir="ltr"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk3MjA4NDI5MTg2LWFraWRhLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib"></p><h3 dir="ltr">Financial Initiatives and Market Presence</h3><p dir="ltr">To wrap up the podcast, Ken Scarance, BrainChip's Chief Financial Officer, touched upon the company's recent financial endeavours. He highlighted the company's agreement with LDA, aimed at raising capital, and BrainChip's strategic move to enhance its presence in the U.S. capital markets. Additionally, the company is bolstering its investor relations strategy, aiming to foster better communication with stakeholders and educate the market about BrainChips groundbreaking offerings.</p><h3 dir="ltr">Conclusion</h3><p dir="ltr">As BrainChip continues to make strides in the AI domain, the company remains committed to keeping its audience informed and engaged. With a series of events lined up to showcase Akida's capabilities and an unwavering focus on innovation, BrainChip is undoubtedly poised to redefine the boundaries of AI.<a href="https://www.wevolver.com/profile/brainchip" target="_blank" rel="noopener noreferrer">&nbsp;Stay up to date with BrainChip's new content here.</a></p>

BrainChip's leadership shares details on the company's development of the Akida chip, future prospects, and more in this informative podcast. 

BrainChip Podcast Leadership Roundtable: These are Exciting Times

<p id="isPasted">RISC-V is inevitable - it became the mantra of RISC-V, and it's true. But before we see why that is, let’s step back and discuss what RISC-V is and why we should care.</p><p>Back in the early days, computers were large and bulky, taking up entire rooms and making a lot of noise.</p><p>It's incredible to think about how much technology has advanced over the years. Nowadays, we're surrounded by microprocessors that make our lives easier without us even realizing it. For example, when we use our bank cards to pay at the supermarket, we're actually using a full computer that encrypts, signs and verifies our transactions. And our phones contain dozens and dozens of processors that make all the conveniences of modern life possible.</p><h2>What is RISC-V?</h2><p>RISC-V (Reduced Instruction Set Computers) is an open-source Instruction Set Architecture (ISA). You may have heard of other well-known ISAs such as x86, ARM, Power, and MIPS.&nbsp;</p><p>The RISC-V ISA is the common, standardized language between the processor (hardware) and the programs running on it (software). With RISC-V, the processor itself can only do very basic things, such as (conditionally) adding or subtracting two numbers and deciding what to do based on those arithmetic outcomes. It can also repeat those arithmetic operations several times until a certain condition is reached. In fact, there are only 37 instructions in the base. But these are the very basic ingredients needed to describe essentially any problem to the processor.&nbsp;</p><p>We call those commands, instructions.&nbsp;</p><p>By defining the exact meaning (semantic) and spelling (syntax) of those instructions, you can start to build a common understanding between the processor and the software running on it. You can think of the ISA as a dictionary. The ISA of RISC-V is free for anyone to access here. This is incredibly important because today’s software has become so complex that no single company can manage it alone and a common standard ensures interoperability.&nbsp;</p><p>RISC-V came to the right place, by the right people, at the right time.&nbsp;</p><p>David Patterson, a visionary in the field of computer architecture, spearheaded the development of Reduced Instruction Set Computers (RISC) at Berkeley. The project went through five iterations, which ultimately led to the creation of the RISC-V architecture.</p><p>Initially, RISC-V mainly piqued academic curiosity. However, the availability of open-source processor implementations, coupled with rising geopolitical tensions, quickly drew industrial interest as well. From that point, the project experienced a snowball effect gaining momentum and broader adoption.</p><h2>Open source breeds innovation</h2><p>The primary advantage of RISC-V lies in its licensing flexibility. Although the specifications for other ISAs are publicly available, legal constraints prevent you from implementing and selling processor hardware unless you have obtained a license for the ISA specification. With RISC-V, this limitation is removed, offering greater freedom for innovation and commercialization.</p><p>The limits that most ISAs have reduce their use by smaller innovators. For example, the widely used ISA “x86” allows only a handful of licensees. Arm, another well-known provider of processor IP, has an entirely different business model. They are selling processor IPs that can be licensed and integrated into your product. Only the biggest players in the market are able to own an architectural license that allows them to implement their own processors.&nbsp;</p><p>Most notable of these is Apple, which switched its entire product line from Intel x86 processors to its own Arm implementation. Their investment in this endeavor proved to be a wise decision both technically and economically, as it enabled them to distinguish their product line even further and surpass their rivals by a significant margin.</p><p>In the past, designing your own processor and utilizing the expansive software ecosystem was thought to be reserved solely for large corporations. However, that's not entirely true. Alternatives like OpenRISC existed, but they weren't widely adopted because their software ecosystems were underdeveloped, and they were often considered hobbyist projects.</p><p>Another notable benefit of RISC-V is its built-in modularity, which contrasts with ARM's more rigid structure. The RISC-V architecture is designed from the ground up to be modular, allowing for easier customization and innovation. While ARM tightly controls and protects its ISA specification, making it difficult to introduce your own specialized features, RISC-V offers the flexibility to add custom extensions and your “secret sauce.”</p><p>This is particularly advantageous if you aim to target specific market segments and differentiate your product from competitors. Remember those 37 instructions I’ve mentioned? Turns out this is only the very base instruction set. For most applications, you would likely want to include some more specialized instructions such as floating-point support, atomic memory operations, or maybe even scalable vector extensions. You don’t need to, but you can. In the same way, your company could add your own instructions in case those are beneficial for the application in mind. This means you can still leverage the entire software ecosystem that has been and is being built and only add value on top instead of reinventing the wheel. So let’s have a look at some of these advantages.&nbsp;</p><h2>How can RISC-V help start-ups design their own chips?</h2><p>For me, the two most important aspects for a hardware-producing start-up are time-to-market and freedom to innovate.&nbsp;</p><p>Most silicon/hardware start-ups innovate and try to provide value-add in their niche. The processor is a necessary, boring commodity and usually not the main star of the product. This is good and the way it should be. Otherwise, we would all be selling the same processors.&nbsp;</p><p>RISC-V is an absolute game changer for that.&nbsp;</p><p>Do you want to quickly try out an integration idea? Prototype something on an FPGA? Before RISC-V this either meant you needed to use some custom FPGA vendor’s ISA (which you couldn’t send to manufacture for your final product) or start negotiations with the processor vendor of your choice. Negotiations are hard for a small silicon start-up. With RISC-V you can go and grab some core from the internet, do your trials, and start building your software stack. Once happy with the prototype and you want to move forward, there are a plethora of RISC-V IP vendors you can choose from. Choice and market competition are a good thing.</p><p>Expanding on the points raised earlier, the freedom to innovate with RISC-V comes without the risk of architectural lock-in. This has two advantages, first, you are free to switch IP vendors. Your software stack will still work the same because you adhered to an open standard. Second, you can provide your own extensions on top of the main RISC-V standards, and the company can provide very concentrated value-add without the need to maintain or develop commodity.&nbsp;</p><h3>Let’s have a look at what we’ve done at Axelera.&nbsp;</h3><p>At the heart of our Metis AI Processing Unit, there are four AI Cores. Each AI core provides a 512x512 matrix-vector multiplication (MVM) in-memory compute array and a vector datapath that operates on streams of data.&nbsp;</p><p>To provide a generic solution that can keep up with the fast evolution in the field of neural networks we kept the datapath control as flexible as possible. We aim to push as much as possible into low-level driver software where we can innovate, correct, and adapt throughout the product’s life cycle. Therefore, each AI Core has a dedicated RISC-V, application-class core, that has full control over the datapath unit. A 5th system controller provides SoC management and workload dispatch to the individual AI cores. We’ve confidently chosen the RISC-V ISA because we could start virtual prototyping and building our software stack on open and free software far before we had done any IP negotiations. Furthermore, we knew that the IP landscape would provide us with sufficient competitive choices for our needs.</p><p>&nbsp;In roughly a year, we went from concept/FPGA prototype to tape-out, and in just a couple of days after having received the chips back, we could run the first end-to-end neural networks on our lab benches. Taking the limited resources and this aggressive time schedule into account it was clear that we’ll needed to buy proven IP without long negotiations to kick-start our developments.&nbsp;</p><p>Choosing to proceed with RISC-V ensured that we could continue to innovate in future generations and further distinguish our offerings.</p><p>So, is it all love, peace, and harmony? Not exactly. Like anything that's still a work in progress. RISC-V has its own set of hiccups and curveballs.</p><p>An ISA is mainly about instructions, but a processor is part of a bigger system that includes memory, peripherals, and other processors. This broader setup, often called a platform, isn't covered in the main ISA spec. The RISC-V Foundation aims to standardize these aspects too.</p><p>However, details matter. Things like atomic handling in multi-hart systems may only be standardized for specific platforms. Also, some IP providers might have legacy elements because they developed solutions before RISC-V standards were set. Standards are scattered, so you have to keep an eye out. And given the rapid growth, it's tough to stay updated on all the ongoing activities.</p><h2>Looking ahead</h2><p>Remember those room-filling mainframes and how technology has continuously shrunk down to fit our pockets and wrists? Just like those evolutionary leaps, RISC-V aims to be a cornerstone in the next phase of computational progress.</p><p>In an ideal future, RISC-V will be as "boring" as any well-established technology—boring in the sense that it's reliable, stable, and so embedded in our daily lives that we take it for granted. The long-term vision is for software to run seamlessly on RISC-V-based processors without users having to worry about compatibility issues.</p><p>In the short term, however, there's still much to be done. While RISC-V is showing promise in deeply embedded systems like smartcards and IoT devices, achieving the same level of support and efficiency as ARM and x86 in more user-centric applications—like your phone or computer—is an ongoing project. Industry trends, as evidenced by companies like SiFive and Ventana and initiatives like the RISE project, suggest a competitive and collaborative future for RISC-V. From a research standpoint, its open nature makes it a fertile ground for innovation across the entire hardware-to-software stack.</p><p>There's a palpable sense of momentum behind RISC-V, with heavyweight stakeholders and top-tier companies pooling their resources and expertise. Far from slowing down, the ecosystem around RISC-V is only gaining speed, setting it on a course to become as ubiquitous and "boring" as the microprocessors that have come to define modern life.&nbsp;</p><p>So, looking at where things are going, ignoring RISC-V would be like missing the boat when we switched from those giant mainframes to desktop PCs. It's a game-changer, and you really don't want to be left behind.</p>

RISC-V Evolution: From Early Computing to Tomorrow's Tech Promise 

Harnessing the RISC-V Wave: The Future is Now

Optimizing AI for the Future: Model Efficiency and Scalability


Intelligence at Scale Through AI Model Efficiency

<p>In today&rsquo;s evolving technology landscape, AI is not merely &ldquo;artificial&rdquo;; it is artfully intelligent. But unlike art, AI&rsquo;s practical applicability requires high levels of efficiency, a challenge the industry still grapples with.</p><p>Particularly with deep neural networks, we seem to encounter a challenge. While these networks dazzle us with their ability to recognize faces, translate languages, and make complex decisions, they also come with a voracious appetite for resources. High memory, compute power, and energy consumption have become almost defining characteristics of contemporary AI models, holding AI back from true ubiquity and rendering the need for operational efficiency ever more pressing.</p><p>In this article, we take a deeper look into Qualcomm AI Research&rsquo;s model efficiency research aimed at enhancing power efficiency and boosting AI performance. From the intricacies of Neural Architecture Search (NAS) to the groundbreaking quantization methods, we will discover how Qualcomm AI Research is leading the charge to unlock the full potential of AI.</p><h2 dir="ltr">Qualcomm AI Research&#39;s Focus on Model Efficiency</h2><p dir="ltr"><a href="https://www.qualcomm.com/research/artificial-intelligence/ai-research" target="_blank">Qualcomm AI Research</a> is at the cutting edge of AI, committed to tackling the intricate challenge of AI model efficiency through practical strategies that aim to enhance both power efficiency and performance. With its aim to make AI&rsquo;s core capabilities ubiquitous across devices, Qualcomm AI Research has adopted a holistic approach to AI model efficiency, delving into the practical aspects of full-stack AI optimization.&nbsp;</p><p>Addressing AI&#39;s resource-intensive nature requires an approach that encompasses machine learning hardware, software, and algorithms. As a result, their research efforts aim to ensure that AI systems operate efficiently without compromising functionality, making AI more adaptable and efficient across a diverse range of devices, particularly mobile devices. As Jilei Hou, VP Engineering at Qualcomm AI Research, states, &ldquo;Our holistic systems-approach to full-stack AI is accelerating the pipeline from research to commercialization.&rdquo;</p><p>But what exactly is this holistic approach to AI model efficiency? How is it implemented, and what angles does Qualcomm AI Research tackle the model efficiency challenge from?</p><h2 dir="ltr">A Holistic Approach to AI Model Efficiency</h2><p dir="ltr">Qualcomm AI Research&#39;s mission to unlock the full potential of AI centers around a comprehensive strategy that attacks the model efficiency challenge from multiple angles. This multifaceted approach is driven by the recognition that optimizing AI models requires a combination of techniques.</p><p>Basically, there is no one-size-fits-all solution to AI model efficiency. &nbsp;Just like art, shrinking AI models down and running them efficiently on hardware can and should be approached in multiple ways, including quantization, compression, Neural Architecture Search (NAS), and compilation.</p><p>Qualcomm AI Research is a strong believer in <a href="https://www.qualcomm.com/news/onq/2019/03/heres-why-quantization-matters-ai" target="_blank">quantization</a> as evidenced by their leading research and products in the market. Quantization enables the AI model to run efficiently on dedicated hardware, thus enhancing its performance while minimizing its consumption of power and memory bandwidth. With focus on quantization-aware training and post-training quantization, Qualcomm AI Research&rsquo;s results demonstrate how effective integer inference is in improving the tradeoff between accuracy and on-device latency.</p><p>With compression, Qualcomm AI Research aims at reducing the size of AI models without compromising their functionality by removing parameters. In other words, with no sacrifice to model accuracy, Qualcomm AI Research&rsquo;s compression technique systematically removes activation nodes and connections between nodes, rendering the AI model smaller and more efficient. Quantization and compression of neural networks are supported by Qualcomm Innovation Center&rsquo;s <a href="https://github.com/quic/aimet" target="_blank">AI Model Efficiency Toolkit (AIMET)</a> library.</p><p>Another approach is Neural Architecture Search (NAS). Their research in NAS focuses on automating the design of efficient neural networks that are much smaller than a large state-of-the-art model. Qualcomm AI Research seeks to develop search algorithms and methodologies that automatically create optimal network architectures tailored to specific tasks. This streamlines the process of designing AI models, enhancing their efficiency and performance.</p><p>Furthermore, advanced compilation techniques optimize the execution of AI models on various hardware platforms. By tailoring AI models to the underlying hardware architecture, they ensure that the models run efficiently, achieving the desired performance while conserving resources.</p><p>In the following subsections, we look deeper into quantization and NAS, highlighting how Qualcomm AI Research is enabling these approaches to unlock AI&rsquo;s potential even further.</p><h3 dir="ltr">A Closer Look at Quantization</h3><p dir="ltr">Quantization reduces the number of bits necessary for representing information in the weights and activations of AI models, boosting power efficiency and performance while reducing memory bandwidth and storage. It also helps enable simultaneous use of multiple AI models, a use case found in demanding application areas like mobile, automotive, and XR.</p><p>Qualcomm AI Research has been at the forefront of research in quantization techniques that are revolutionizing power-efficient AI. Their research covers both quantization-aware training and post-training quantization for efficient integer AI inference. Their products support quantization down to 4-bit integers, showcasing their commitment to making AI more power-efficient.&nbsp;</p><p>In fact, some of their recent<a href="https://arxiv.org/abs/2203.11086" target="_blank">&nbsp;findings</a> revealed issues that affect model accuracy, one of which is oscillating weights during model training. With state-of-the-art (SOTA) methods called oscillation dampening and iterative freezing, accuracy is improved even for under 4-bit quantization. Qualcomm AI Research has also explored the role of <a href="https://www.qualcomm.com/news/onq/2023/04/floating-point-arithmetic-for-ai-inference-hit-or-miss" target="_blank">floating-point arithmetic</a> in AI inference, shedding light on the balance between precision and efficiency. This research considers the trade-offs involved in using floating-point or integer representations in AI models, concluding that integer inference is the best approach. Another recent study on post-training quantization (PTQ) and its impact on softmax activation highlights a technique proposed by Qualcomm AI Research, called <a href="https://arxiv.org/abs/2309.01729" target="_blank">offline bias correction</a>. With this method, one can enhance the quantizability of softmax with no additional compute during deployment, thus significantly improving the accuracy for 8-bit quantized softmax.</p><p>Quantization is a highly-effective approach to AI model efficiency. Qualcomm AI Research&#39;s leading quantization research combined with Qualcomm&rsquo;s leading processor solutions with AI acceleration supporting 8-bit or 4-bit integers has resulted in industry leading performance per watt, showing the importance of tailoring AI models to the specific constraints of edge devices.</p><h3 dir="ltr">Neural Architecture Search (NAS)</h3><p dir="ltr">With Neural Architecture Search (NAS), Qualcomm AI Research focuses on automating the design and training of efficient neural networks, aligning them more closely with dedicated tasks and optimizing their overall performance. NAS consists of four components:</p><ul><li dir="ltr"><p dir="ltr">A search space (what types of networks can be searched over)</p></li><li dir="ltr"><p dir="ltr">An accuracy predictor (how accurate a network should be)</p></li><li dir="ltr"><p dir="ltr">A latency predictor (how fast a network will run)</p></li><li dir="ltr"><p dir="ltr">A search algorithm (what the best architecture is for a particular task)</p></li></ul><p>However, NAS still presents some intricate challenges, particularly in defining an expansive search space, where countless network architectures can be explored. This space represents the potential configurations that an AI model could take. The challenge lies in navigating this vast terrain to discover the most efficient and effective neural network for a given task, as well as addressing the high compute cost, unreliable estimates for hardware performances, and inefficient scaling of existing methods.</p><p>That&rsquo;s why Qualcomm AI Research has addressed these challenges with their NAS research called <a href="https://arxiv.org/pdf/2012.08859.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">DONNA (short for Distilling Optimal Neural Network Architectures)</a>.</p><h4 dir="ltr">DONNA: Distilling Optimal Neural Network Architectures</h4><p dir="ltr">An efficient NAS with hardware-in-the-loop optimization, DONNA is a scalable method capable of finding optimal network architectures with high accuracy and minimal latency for virtually any hardware platform at low cost. This revolutionary method tackles the model deployment challenges in real scenarios effectively thanks to its:</p><ul><li dir="ltr"><p dir="ltr">Diverse search space</p></li><li dir="ltr"><p dir="ltr">Low compute cost</p></li><li dir="ltr"><p dir="ltr">Scalability</p></li><li dir="ltr"><p dir="ltr">Reliable direct hardware measurement</p></li></ul><p>Its diverse search space includes the usual variable kernel-size, expansion-rate, depth, channel number, and cell-type, but can also search over activations and attention, a vital parameter to finding optimal architectures. Its hardware predictor is hardware agnostic with a low startup cost, enabling NAS to scale to multiple hardware devices at low costs. Furthermore, DONNA is able to capture the run-time version and hardware architecture, enabling users to find real and accurate latency values rather than simulated ones.</p><p>DONNA also has pre-trained blocks that enable fast fine-tuning of neural networks to fast track reaching full accuracy and is a single scalable solution, applying, for instance, directly to downstream tasks and non-CNN neural architectures with no need for conceptual code changes.</p><h2 dir="ltr">Open-Source AI Model Efficiency Projects</h2><p dir="ltr">Qualcomm AI Research believes that open-source projects are a great way to share knowledge for scaling model-efficient AI to the masses. That&rsquo;s why Qualcomm Innovation Center has provided two open-source GitHub projects based on Qualcomm AI Research&rsquo;s advanced research:</p><ul><li dir="ltr"><p dir="ltr"><a href="https://www.qualcomm.com/news/onq/2020/05/open-sourcing-ai-model-efficiency-toolkit" target="_blank">AI Model Efficiency Toolkit (AIMET)</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://www.qualcomm.com/news/onq/2021/01/aimet-model-zoo-highly-accurate-quantized-ai-models-are-now-available" target="_blank">AIMET Model Zoo</a></p></li></ul><p>AIMET is a toolkit that offers advanced quantization and compression techniques, while AIMET Model Zoo offers pre-trained 8-bit quantized models with high accuracy. With these open-source projects, Qualcomm aims to boost the transition to fixed-point quantized models, which would radically enhance AI applications, particularly those requiring high performance, low latency, and low power consumption, such as mobile platforms.</p><h2 dir="ltr">Advancing the AI Frontier</h2><p dir="ltr">As Qualcomm&rsquo;s OnQ blog series states, &ldquo;<a href="https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/documents/Whitepaper-The-future-of-AI-is-hybrid-Part-1-Unlocking-the-generative-AI-future-with-on-device-and-hybrid-AI.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">The future of AI is hybrid</a>&rdquo;, AI is evolving in that direction, with AI processing being distributed between edge devices and the cloud. On-device AI provides benefits in cost, power consumption, performance, personalization, privacy, and security. But for all this to happen, model efficiency is key, and that&rsquo;s where Qualcomm is leading the pack as the on-device AI leader.</p><p>Qualcomm AI Research envisions a future where AI processing is highly efficient for all devices across all applications all over the world. With generative AI pushing the computing requirements even higher, Qualcomm&rsquo;s focus on efficiency and performance alongside their open ecosystem is enabling generative AI and other upcoming revolutionary technologies.</p><p>Whether it&#39;s the quantization approach, NAS (and DONNA), compression, or compilation, Qualcomm AI Research will continue to find and develop ways of making AI processing ever more efficient so you and I can enjoy the perks of amazing AI technologies on almost every device you could think of.</p><p>Join Qualcomm&rsquo;s open-source projects (<a href="https://www.qualcomm.com/news/onq/2020/05/open-sourcing-ai-model-efficiency-toolkit" target="_blank">AIMET</a> and <a href="https://www.qualcomm.com/news/onq/2021/01/aimet-model-zoo-highly-accurate-quantized-ai-models-are-now-available" target="_blank">AIMET Model Zoo</a>) and be part of the transformation towards efficient AI processing. Interested in learning more about Qualcomm AI Research&rsquo;s work, check out the following links:</p><ul><li dir="ltr"><p dir="ltr"><a href="https://assets.qualcomm.com/MCC-ALL-Q322-0915-WB-ThefutureofmodelefficiencyforedgeAI_01RegistrationPage.html" target="_blank">The Future of Model Efficiency for Edge AI (on-demand webinar)</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/documents/Whitepaper-The-future-of-AI-is-hybrid-Part-1-Unlocking-the-generative-AI-future-with-on-device-and-hybrid-AI.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">The future of edge AI is hybrid (whitepaper)</a></p></li><li dir="ltr"><p dir="ltr"><a href="https://www.qualcomm.com/news/onq/2023/08/5-benefits-of-on-device-generative-ai" target="_blank">5 benefits of on-device generative AI</a></p></li></ul><p><a href="https://assets.qualcomm.com/mobile-computing-newsletter-sign-up.html" target="_blank">Sign up for our What&#39;s Next in AI and Computing newsletter</a>&nbsp;</p>

Live translation devices will benefit from advances in model efficiency. Image credit: TimeKettle

Model efficiency research is enhancing power efficiency and boosting AI performance.

Unlocking the Full Potential of AI: A Deep Dive into Qualcomm's Model Efficiency Research

<p id="isPasted">This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;</p><p><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/50b8e0ea-1cdb-4b34-87e6-4867feefade3?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p><p>The full article will continue below.</p><hr><p><em>This is the second article in a short series. Read the<a href="https://www.wevolver.com/article/balancing-the-cloud-and-the-edge-a-close-look-at-enabling-hybrid-ai" target="_blank" rel="noopener noreferrer">&nbsp;first piec</a>e here.</em></p><h2 dir="ltr" id="isPasted">Introduction</h2><p dir="ltr">Generative AI is a rapidly advancing field of artificial intelligence (AI) focused on creating novel data assets like images, text, or music. Such AI models are trained using extensive datasets, enabling them to create new data resembling what they were trained on. The growth in generative AI's development owes itself to several key factors: availability of large datasets, improved computing hardware capabilities, and the evolution of novel machine learning (ML) algorithms and architectures.</p><p dir="ltr">Large language models–based chatbots like ChatGPT, which can generate coherent and contextually relevant text and even images, have gained the interest and creativity of researchers, businesses, and the public. Generative models have demonstrated remarkable capabilities across a range of applications, from natural language understanding and text generation to creative content creation and even virtual assistants. However, as these models grow in complexity and sophistication, they bring to the forefront an increasingly pressing issue in the form of scalability challenges that apply to both training and inference.&nbsp;</p><p dir="ltr">These challenges encompass the need for significant computational resources, the growing size of models, and increasing costs. Latency and real-time responses primarily relate to the inference phase, while ethical considerations, interoperability, privacy, energy consumption, and cost management are critical factors throughout the entire lifecycle of AI systems, including training and inference.&nbsp;</p><p dir="ltr">One promising solution arises in response to these challenges - on-device AI. Deploying AI models directly on user devices (like smartphones and tablets) offers multiple advantages. It reduces reliance on cloud resources, cutting computational and energy costs. It improves privacy by processing data locally, reducing the need to send sensitive information to the cloud. It also lowers latency, supports offline functionality, and aligns with sustainability goals by reducing energy consumption.</p><h2 dir="ltr">What is Hybrid AI?</h2><p dir="ltr">To properly define Hybrid AI, we need to introduce the terms on-device AI and hybrid AI. On-Device AI, also known as edge AI or local AI, refers to the deployment of AI algorithms and models directly on user devices (smartphones, tablets, IoT devices, autonomous vehicles, etc.), without heavy reliance on cloud-based infrastructure. It enables real-time processing and decision-making on the device itself, reducing the need for constant data transmission to remote servers. Hybrid AI represents a synergy between local devices and cloud infrastructure, strategically dividing AI computations to optimize both user experiences and resource efficiency.</p><p dir="ltr">In certain situations, AI processing predominantly occurs on the device, with the option to delegate tasks to the cloud as needed. In cloud-centric setups, devices will opportunistically offload AI workloads from the cloud, where possible and subject to their capabilities. Employing a hybrid AI architecture, or relying solely on on-device AI, yields numerous advantages including cost savings, improved energy efficiency, enhanced performance, heightened privacy and security, and personalized experiences on a global scale.</p><p dir="ltr">Within a hybrid AI framework, on-device AI processing delivers consistent performance that can rival or surpass cloud-based alternatives, particularly in scenarios characterized by congested cloud servers and network connectivity issues. Instances of high demand for generative AI queries in the cloud can result in lengthy queues and elevated latency, and in extreme cases, lead to service disruptions. These challenges can be mitigated by redistributing computational workloads to edge devices.</p><p dir="ltr">Furthermore, the presence of on-device processing capabilities in a hybrid AI architecture enables generative AI applications to function seamlessly in locations with limited or no connectivity. In a device-centric hybrid AI setup, the device serves as the central point of operation, with cloud resources primarily utilized for tasks that exceed the device's processing capacity. Given that many generative AI models can efficiently run on the device, edge devices can handle the bulk of the processing load. As the development of on-device AI continues, it holds significant potential to revolutionize AI service deployment and user experiences while maintaining a balance between performance and ethical considerations.</p><h2 dir="ltr">Unique Benefits of On-Device AI</h2><p dir="ltr"><a href="https://www.qualcomm.com/news/onq/2023/08/5-benefits-of-on-device-generative-ai" target="_blank">On-device AI offers several unique benefits</a>, including:</p><h3>Cost-efficiency&nbsp;</h3><p>By processing data locally, it reduces the need for extensive cloud infrastructure, which can be expensive to maintain and scale. On-device processing eliminates the necessity of sending data to the cloud, a process that can be both expensive and time-consuming. &nbsp;For instance, on-device AI for image generation, can be employed to generate high-quality images in real-time without relying on cloud-based servers. A mobile photography application equipped with generative AI can apply artistic filters, improve image quality, or create artistic effects directly on the user's device.&nbsp;</p><p>This ensures that users can quickly and seamlessly edit and generate images without uploading them to a remote server, preserving both privacy and reducing latency. Additionally, it allows for offline image generation, enabling users to create and edit images even when they're in locations with poor or no internet connectivity. This level of on-device image generation can significantly improve the user experience and provide powerful tools for content creation without compromising data privacy or speed.&nbsp;</p><h3>Energy Savings&nbsp;</h3><p>On-device AI mitigates the issue of energy consumption by performing computations locally. This is particularly crucial for devices with constrained battery life, like smartphones and wearables. Comparing the power efficiency of running generative AI models on edge devices versus to the cloud, edge devices offer superior performance per watt and reduced energy consumption, potentially resulting in environmental and cost benefits.&nbsp;</p><h3>Performance and Low Latency</h3><p>By processing tasks locally, it minimizes communication and computing delays associated with cloud-based AI. This is particularly important in real-time applications such as autonomous vehicles, medical devices, and interactive content, where even milliseconds of delay can have a significant impact on functionality and user experience.</p><h3>Enhanced Privacy and Security</h3><p>This approach reduces the risk of data breaches and unauthorized access during data transfer and cloud storage. Users can have greater confidence that their personal information remains on their devices, reinforcing privacy and security standards, especially for applications handling sensitive data, like financial transactions and medical information.</p><h3>Personalization and User Experience</h3><p>These models can adapt to the user's context and needs, improving user experiences by recommending relevant products or services based on their preferences and current circumstances. For example, a shopping application could use on-device AI to recommend products similar to past purchases or consider the user's location and weather conditions. Real-time personalization boosts relevance, engagement, and customer satisfaction.</p><h2 dir="ltr">Case Studies: On-Device AI in Action</h2><p dir="ltr">The following case studies illustrate the transformative potential of on-device AI across various domains, showcasing its benefits.</p><h3 dir="ltr" id="isPasted">Automotive</h3><p dir="ltr">In the automotive industry, AI-driven cockpits are revolutionizing the driving experience. These systems, like those in smartphones and PCs, are starting to employ in-vehicle digital assistants powered by generative AI to create highly personalized and hands-free interactions for drivers and passengers.&nbsp;</p><p dir="ltr">These digital assistants leverage personal and vehicle sensor data, including cameras and microphones, to improve the driving journey. Third-party services can also integrate seamlessly, improving navigation, offering proactive assistance, and enabling in-car commerce, such as ordering food. Furthermore, the cockpit experience is improved through individual recognition, customization of media content, and the rise of in-vehicle augmented reality. Vehicle maintenance becomes proactive as AI digital assistants analyze data to predict maintenance needs, to seamlessly communicate with users using natural language, and to provide precise repair guidance. This proactive approach not only enhances reliability but also effectively reduces costs.&nbsp;</p><p dir="ltr">Qualcomm, which leads the field in cockpit and in-vehicle infotainment solutions with numerous global automakers choosing Snapdragon® Cockpit Platforms. These platforms power digital cockpits, with many already in production or design stages. Partners include Honda, Mercedes, Renault, Volvo, and others. The Snapdragon Cockpit Platform's latest iteration focuses on superior in-vehicle user experiences, safety, comfort, and reliability, setting new standards for connected car digital cockpit solutions. Qualcomm's Snapdragon Ride™ Platform complements this, offering scalable automated driving SoC platforms for ADAS, featuring vision perception, parking, and path planning.</p><p dir="ltr"><span class="fr-img-caption fr-fic fr-dib" style="width: 302px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk1NjUyNzU0OTg0LXF1YWxjb21tIGNhYmluLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib"><span class="fr-inner" spellcheck="false">&nbsp;Cockpit platforms are designed to transform in-vehicle experiences, supporting higher levels of compute and computing intelligence needed for advanced capabilities featured in next generation vehicles. Image credit: Qualcomm.</span></span></span></p><h3 dir="ltr" id="isPasted">Extended Reality</h3><p dir="ltr">For Extended Reality (XR), generative AI has the potential to democratize 3D content creation. In the near future, AI rendering tools will enable content creators to generate 3D objects and entire virtual worlds using various inputs like text, speech, images, or video. Furthermore, text-to-text models will facilitate lifelike conversations for avatars, transforming the way we interact with XR content. Despite the exciting possibilities, widespread adoption timelines remain uncertain, though significant progress is expected soon. Immersive XR experiences will benefit from text-to-image models for realistic textures, likely available on smartphones and XR devices within a year.&nbsp;</p><p dir="ltr">These capabilities will involve distributed processing, with headsets handling perception and rendering, while generative AI models run on paired smartphones or in the cloud. In a few years, text-to-3D and image-to-3D models will likely produce high-quality 3D objects, evolving to generate entire scenes and rooms. Eventually, XR may enable users to immerse themselves in virtual worlds constructed from their imagination. Virtual avatars will undergo a similar evolution, utilizing text-to-text models for natural conversations and text-to-image models for outfits. Over time, avatars may become increasingly photorealistic, fully animated, and mass-producible, driven by image-to-3D and encoder/decoder models. This progression promises to revolutionize how we create and experience immersive XR content, with continual advancements anticipated in the years ahead.</p><p dir="ltr"><span class="fr-img-caption fr-fic fr-dib" style="width: 302px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk1NjUzMTYyMjIyLUNhbm5lcy1YUi1WaXJ0dWFsLUJyaW5ncy1JbW1lcnNpdmUtQXJ0LXRvLUxpZmUtV2l0aC1WaXJ0dWFsLVJlYWxpdHkucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib"><span class="fr-inner" spellcheck="false">Image credit: Cannes</span></span></span></p><h2 dir="ltr">Challenges and Solutions</h2><p dir="ltr">The technical challenges specific to hybrid AI are being actively addressed through ongoing research and innovation:</p><h3 dir="ltr">Model size</h3><p>Model size is a notable challenge, particularly on resource-constrained devices. As large models are challenging to store and run efficiently, a potential solution involves employing compression and quantization techniques to reduce model size while maintaining accuracy. <a href="https://stackoverflow.blog/2023/08/23/fitting-ai-models-in-your-pocket-with-quantization/" target="_blank">Qualcomm</a> is actively researching ways to enhance <a href="https://www.qualcomm.com/news/onq/2019/03/heres-why-quantization-matters-ai" target="_blank">quantization</a> techniques, specifically aiming to quantize 32-bit floating point parameters to 8-bit or 4-bit integers in neural networks while maintaining accuracy. The research encompasses various model quantization methods, such as Bayesian learning, adaptive rounding, and transformer quantization, as part of <a href="https://www.qualcomm.com/research/artificial-intelligence/ai-research" target="_blank">Qualcomm AI Research</a>'s ongoing efforts.&nbsp;</p><p>For instance, the Qualcomm AI Research team employed the <a href="https://www.forbes.com/sites/davealtavilla/2023/05/15/powering-ai-on-mobile-devices-requires-new-math-and-qualcomm-is-pioneering-it/?sh=54cb40c91a16" target="_blank">AIMET</a> tool (AI Model Efficiency Toolkit) to quantize the 32-bit floating point Stable Diffusion AI model into an 8-bit integer format while preserving almost the same accuracy level. By optimizing and scaling the model for INT8 precision operations instead of FP32, Qualcomm successfully enabled Stable Diffusion to run efficiently on handheld devices without internet connectivity, significantly reducing the model's size while maintaining accuracy and enhancing performance on low-power Snapdragon AI accelerators.</p><h3>Computational power</h3><p>Large AI models may place heavy computational demands, particularly on devices with restricted processing capabilities. A potential solution involves leveraging specialized hardware like AI accelerators to enhance AI model performance on such devices. In 2022, Snapdragon 8 Gen 2 provided groundbreaking AI, integrated across the entire system, powered by their fastest, most advanced Qualcomm AI Engine to date. Users can experience faster natural language processing with multi-language translation or have fun with AI cinematic video capture.&nbsp;</p><p>The latest Hexagon Processor introduced a dedicated power delivery system, which adapts power according to the workload. Special hardware improves group convolution, activation function acceleration, and the performance of the Hexagon Tensor Accelerator. Support for micro-tile inferencing and INT4 hardware acceleration provide even higher performance while reducing power and memory traffic. The transformer acceleration dramatically speeds up inference for multi-head attention that is used throughout generative AI, resulting in AI performance up to 4.35X on certain use cases with MobileBERT.&nbsp;</p><p dir="ltr">These ongoing research efforts are addressing the technical challenges of hybrid AI, with expectations to overcome them successfully as the technology advances and becomes more widely adopted and utilized.</p><h2 dir="ltr">Conclusion</h2><p dir="ltr">On-device AI plays a critical role in addressing the future scalability challenges of generative AI models. It has the potential to revolutionize numerous industries and significantly enhance user experiences. By enabling local processing and real-time personalization, on-device AI reduces the dependence on cloud resources, improves privacy and security as well as the efficiency of AI applications. This approach not only supports the responsible development of AI technologies but also opens new possibilities for scalable and personalized AI solutions across diverse sectors, from healthcare to entertainment, promising a brighter future for both businesses and users alike.</p><p>To stay up to date on the latest from Qualcomm, <a href="https://assets.qualcomm.com/mobile-computing-newsletter-sign-up.html" target="_blank">join the “What’s Next in AI and Computing” newsletter</a> and read their hybrid AI whitepapers (<a href="https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/documents/Whitepaper-The-future-of-AI-is-hybrid-Part-1-Unlocking-the-generative-AI-future-with-on-device-and-hybrid-AI.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">part 1</a>, <a href="https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/documents/Whitepaper-The-future-of-AI-is-hybrid-Part-2-Qualcomm-is-uniquely-positioned-to-scale-hybrid-AI.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">part 2</a>)</p>

How on-device and cloud AI will foster the advancement and scalability of next-generation generative AI experiences

The Scalability Challenge: Focusing on Hybrid AI in the Future of Generative AI Models

Qualcomm's Pioneering Approach to Hybrid AI: Merging Cloud Processing with On-Device Efficiency and Scale


Balancing the Cloud and the Edge: A Close look at Enabling Hybrid AI

<h2 dir="ltr" id="isPasted" data-element-id="headingsMap-4-0">Introduction</h2><p dir="ltr">Gesture recognition is not just a buzzword; it's an indispensable technology that's changing the way we interact with devices. From smartphones to smart homes, the ability to control devices through simple hand movements offers an unparalleled level of convenience and accessibility. However, implementing robust gesture recognition systems is fraught with challenges, from data acquisition and preprocessing to machine learning model training and deployment.</p><p dir="ltr">In this article, we will look into the technical aspects of developing a gesture recognition system using Infineon's PSoC 6 microcontroller. We'll explore each stage of the development process, from sensor data acquisition to neural network model deployment. We'll also share a link to a GitHub project detailing a step-by-step guide on implementing gesture classification, empowering you to create your own gesture recognition application. By the end of this article, you'll have a comprehensive understanding of the complexities involved and how specialized machine learning platforms such as Edge Impulse can simplify the process.</p><p dir="ltr"><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p><h2 dir="ltr" data-element-id="headingsMap-6-0">The Need for Gesture Classification</h2><p dir="ltr">The demand for intuitive human-machine interfaces is growing exponentially across various sectors. Whether it's automotive infotainment systems, medical devices, or consumer electronics, the ability to interact through gestures adds a layer of convenience and user-friendliness. However, implementing these systems on embedded platforms like the PSoC 6 involves challenges such as computational limitations, real-time processing requirements, and power constraints.</p><p dir="ltr">To address these challenges, developers often have to make trade-offs between system performance and complexity. For instance, simpler algorithms may require fewer computational resources but may not provide the desired level of accuracy. On the other hand, complex algorithms may offer high accuracy but may be too resource-intensive for real-time applications. This delicate balance makes the choice of hardware and software platforms crucial in the development process. With these considerations in mind, let's delve into the capabilities of the Infineon PSoC 6 and see how it stands out as a viable solution for these challenges.</p><h2 dir="ltr" data-element-id="headingsMap-7-0">Infineon PSoC 6: An Overview</h2><p dir="ltr">Infineon's PSoC 6 is a versatile microcontroller unit (MCU) designed with low-power IoT applications in mind. It features a dual-CPU architecture, combining an ARM Cortex-M4 and an ARM Cortex-M0+ processor, allowing for efficient task partitioning. The PSoC 6 also offers programmable analog and digital blocks, making it highly customizable for specific application needs. Its rich set of features makes it an ideal candidate for implementing complex tasks like gesture recognition.</p><p dir="ltr"><span class="fr-img-caption fr-fic fr-dib" style="width: 302px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk0OTU2NjAwMjk1LWltYWdlMy5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="infineon-psoc-6-prototyping-kit"><span class="fr-inner" spellcheck="false">Fig. 1: Infineon Technologies PSoC™ 6 Wi-Fi® BT Prototyping Kit. Source:&nbsp;<a href="https://www.mouser.in/new/infineon/cypress-psoc-6-wifi-bt-proto-kit/" target="_blank" rel="noopener noreferrer">Mouser Electronics</a></span></span></span></p><p dir="ltr" id="isPasted">The PSoC 6 is not just a powerful MCU; it's a complete ecosystem that provides developers with a range of tools and libraries to accelerate the development process. From ModusToolbox, a comprehensive software development environment, to a rich set of middleware components, the PSoC 6 ecosystem is designed to simplify complex tasks.</p><h3 dir="ltr" data-element-id="headingsMap-8-0">Sensor Data Acquisition</h3><p dir="ltr">For gesture recognition, sensor data is the raw material. PSoC 6 can interface with a variety of motion sensors, such as accelerometers and gyroscopes, using SPI and UART protocols. These sensors capture the 3D spatial movements that are then classified into specific gestures. However, data acquisition is not just about reading sensor values; it's about doing so reliably and efficiently. Specialized machine learning platforms like Edge Impulse can offer features like sensor fusion and automated data collection, ensuring that the raw data is as accurate as possible.</p><p dir="ltr"><em><strong>Suggested Reading:&nbsp;</strong></em><a href="https://www.wevolver.com/article/what-is-sensor-fusion-everything-you-need-to-know" target="_blank"><strong><em>Sensor Fusion: The Ultimate Guide to Combining Data for Enhanced Perception and Decision-Making</em></strong></a></p><p dir="ltr">Data acquisition in real-world applications is often noisy and inconsistent. Factors like sensor drift, environmental conditions, and hardware limitations can introduce errors into the collected data. Therefore, it's essential to implement robust data acquisition strategies that can mitigate these issues. Techniques like sensor calibration, data validation, and outlier detection are often employed to improve the quality of the collected data.</p><h3 dir="ltr" data-element-id="headingsMap-9-0">Data Preprocessing and Filtering</h3><p dir="ltr">Once the raw sensor data is acquired, it needs to be preprocessed before feeding it into a machine learning model. This involves filtering out noise and normalizing the data. Techniques like Infinite Impulse Response (IIR) filtering and min-max normalization are commonly employed for this purpose. While these preprocessing steps are essential for the accuracy of the final model, they can be time-consuming to implement and optimize. Specialized machine learning platforms can automate much of this, allowing developers to focus on other critical aspects of the system.</p><p dir="ltr">Data preprocessing is not a one-size-fits-all operation; it often requires fine-tuning based on the specific application requirements. For instance, the choice of filter parameters, the window size for normalization, and the sampling rate can all impact the performance of the gesture recognition system. Therefore, it's crucial to perform iterative testing and validation to fine-tune these parameters, a process that can be significantly streamlined using specialized machine learning platforms. Edge Impulse&nbsp;offers&nbsp;intuitive tools for data preprocessing, allowing developers to easily filter and normalize data, ensuring it's ready for model training.</p><h3 dir="ltr" data-element-id="headingsMap-10-0">Neural Network Models for Gesture Recognition</h3><p dir="ltr">Gesture recognition typically employs Convolutional Neural Networks (CNNs) due to their ability to process spatial hierarchies in the data. A standard CNN model for gesture recognition would include multiple layers, such as convolutional layers, Rectified Linear Unit (ReLU) activation functions, max pooling, and batch normalization. These layers work in tandem to extract features from the raw sensor data and classify them into specific gestures. However, training these models requires a deep understanding of machine learning algorithms, data science, and optimization techniques. Specialized machine learning platforms can simplify this process by offering pre-trained models and automated training pipelines.</p><p dir="ltr">The complexity of the neural network model often depends on the number of gestures to be recognized and the required accuracy. More complex models with additional layers and nodes can offer higher accuracy but may be computationally intensive, making them unsuitable for real-time applications on resource-constrained devices like the PSoC 6. Therefore, model optimization techniques like pruning, quantization, and layer fusion are often employed to reduce the computational complexity without significantly compromising accuracy.</p><h3 dir="ltr" data-element-id="headingsMap-11-0">Implementing Gesture Recognition on PSoC 6</h3><p dir="ltr">Developing a gesture recognition system involves more than just machine learning models. The development environment needs to be set up, the hardware configured, and the software architecture designed. In the case of PSoC 6, the ModusToolbox software environment provides a range of tools for configuration and development. The code structure for implementing gesture recognition involves various tasks, such as data acquisition, preprocessing, and classification. FreeRTOS is often used for managing these tasks, offering the benefits of real-time operation and future scalability.</p><p dir="ltr">The software architecture for implementing gesture recognition on PSoC 6 often involves multiple tasks running concurrently. For instance, one task may be responsible for data acquisition, another for data preprocessing, and yet another for gesture classification. Managing these tasks efficiently requires a robust multitasking environment, which is where real-time operating systems like FreeRTOS come into play. FreeRTOS allows for efficient task scheduling, inter-task communication, and resource management, making it easier to develop complex applications like gesture recognition.<span class="fr-img-caption fr-fic fr-dib" style="width: 304px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk0OTU2MTc1NTA3LWltYWdlMi5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 302px;" class="fr-fic fr-dib" alt="edge-AI-gesture-recognition"><span class="fr-inner" spellcheck="false">Fig. 2: Through edge AI techniques, gestures can be translated into data formats comprehensible by computers, enabling efficient real-time processing and decision-making</span></span></span></p><p dir="ltr" id="isPasted">Beyond the software architecture, the deployment phase is also crucial. Once the model is trained and optimized, it needs to be converted into a format that can be loaded onto the PSoC 6 MCU. This often involves converting high-level model formats like H5 into C or C++ code that can be integrated into the ModusToolbox environment. This step can be cumbersome and error-prone if done manually. However, specialized machine learning platforms offer automated tools for model conversion and deployment, ensuring that the transition from development to production is seamless.<span class="fr-img-caption fr-fic fr-dib" style="width: 306px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk0OTU2MjQ4MjM5LXNwYWNlc19HRWdjQ2s0UGtTNVBhNnVCYWJsZF91cGxvYWRzX2dpdC1ibG9iLWQyYjE4YjVmYTMzM2YwYTJjNjMwY2MzYTBlZmM3ZGY3YTNiNDYzYTBfdHV0b3JpYWwtY29udGludW91cy1tb3Rpb24tY3JlYXRlLWltcHVsc2Uud2VicCIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 304px;" class="fr-fic fr-dib" alt="edge-impulse-studio-gesture-recognition"><span class="fr-inner" spellcheck="false">Fig. 3: Designing an Edge AI application for motion recognition using Edge Impulse studio. Source:&nbsp;<a href="https://docs.edgeimpulse.com/docs/tutorials/end-to-end-tutorials/continuous-motion-recognition" target="_blank" rel="noopener noreferrer">Edge Impulse</a></span></span></span></p><p dir="ltr" id="isPasted">The final piece of the puzzle is real-time performance monitoring and updates. Once deployed, the system's performance needs to be monitored to ensure it meets the desired accuracy and latency requirements. Any necessary updates or optimizations can be rolled out as firmware updates, a process that can be automated and streamlined using specialized machine learning platforms.</p><p dir="ltr">As we've seen, the journey from concept to deployment in gesture recognition involves multiple steps, each with its own set of challenges and complexities. While the PSoC 6 provides a robust hardware platform, the software complexities often require specialized tools and platforms for efficient development and deployment.</p><p dir="ltr">Here is a project by Infineon explaining the step by step process to implementing gesture classification using Infineon PSoC 6: <a href="https://github.com/Infineon/mtb-example-ml-gesture-classification" target="_blank">GitHub - Infineon/mtb-example-ml-gesture-classification</a>. For in-depth exploration of more Edge AI projects, don't forget to check out: <a href="https://edgeimpulse.com/blog" target="_blank">Edge Impulse Blog</a>.</p><h2 dir="ltr" id="isPasted" data-element-id="headingsMap-12-0">Conclusion</h2><p dir="ltr">Gesture recognition is poised to become a standard feature in the next generation of human-machine interfaces. While platforms like Infineon's PSoC 6 provide the hardware capabilities for such advanced applications, the development process involves several complexities. These complexities can be significantly simplified by leveraging the power of specialized machine learning platforms like Edge Impulse, making it easier to develop, deploy, and scale robust gesture recognition systems.</p><p dir="ltr"><em><strong>Further reading:&nbsp;</strong></em><a href="https://www.wevolver.com/article/spotlight-on-innovations-in-edge-computing-and-machine-learning-predictive-maintenance" target="_blank"><strong><em>Spotlight on Innovations in Edge Computing and Machine Learning: Predictive Maintenance</em></strong></a></p><h2 dir="ltr" data-element-id="headingsMap-13-0"><em>About the sponsor: Edge Impulse</em></h2><p dir="ltr"><em><a href="https://www.edgeimpulse.com/" target="_blank">Edge Impulse</a> is the leading development platform for embedded machine learning, used by over 1,000 enterprises across 200,000 ML projects worldwide. We are on a mission to enable the ultimate development experience for machine learning on embedded devices for sensors, audio, and computer vision, at scale.&nbsp;</em></p><p dir="ltr"><em>From getting started in under five minutes to MLOps in production, we enable highly optimized ML deployable to a wide range of hardware from MCUs to CPUs, to custom AI accelerators. With Edge Impulse, developers, engineers, and domain experts solve real problems using machine learning in embedded solutions, speeding up development time from years to weeks. We specialize in industrial and professional applications including predictive maintenance, anomaly detection, human health, wearables, and more.</em></p><p dir="ltr"><em><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjk0OTU2NDM1MDUxLWltYWdlMS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="edge-impulse-logo"></em></p><p><span contenteditable="false" draggable="true" class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable"><iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p>

Gesture recognition, leveraging the advanced capabilities of embedded devices and streamlined through specialized platforms is creating new means of human-machine interactions, paving the way for more intuitive and user-friendly device interfaces.

Gesture Recognition and Classification Using Infineon PSoC 6 and Edge AI

<p dir="ltr" id="isPasted">Sevensense Robotics builds the eyes and brains of mobile robots. &nbsp;</p><p dir="ltr">We strive to provide the most flexible and robust Visual AI solutions to give robots the ability to identify, understand, and act on imagery and visual data -captured by cameras- just like humans so that they can navigate autonomously.</p><p dir="ltr">Our technology enables robots to adapt their navigation behavior based on real-time perception, allowing them to complete their missions, for example, docking, picking, or charging, while sharing the floor with moving elements like people and other vehicles.</p><p dir="ltr">To ensure everything we ship has the high performance our customers expect, we stress-test our technology in different challenging settings.</p>

Sevensense Robotics pushes the boundaries of Visual SLAM technology

This is how Sevensense tests its curring-edge Visual SLAM technology to ensure robust performance.

The Sevensense Labs

<p>Tickets are going fast for <strong id="isPasted">Imagine 2023</strong>! Be sure to register for the premier edge AI event. Join us for the live stream on September 27th to hear presentations and demonstrations from top technology leaders and innovators like NVIDIA, Mattel, Know Labs, Lexmark, and more. This exclusive event will explore all the latest innovations in artificial intelligence at the edge.</p><p><br></p><p><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjkyNTY4NzIyMTY2LWs0MnplNXRldHR3Z2FlbngzYXUzLndlYnAiLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 735px;" class="fr-fic fr-dib"></p><p><br></p><p>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<a href="https://wevlv.co/imagineconf" target="_blank" rel="noopener noreferrer"><strong>REGISTER HERE</strong></a></p><h4 id="isPasted">Why Attend?</h4><style type="text/css" id="isPasted">p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 13.0px 'Helvetica Neue'}</style><p>Imagine brings together machine learning industry leaders, visionaries, and researchers to discuss cutting-edge developments and solutions through presentations, panels, and hardware demos.&nbsp;</p><p>From engineers and developers to C-suite executives and entrepreneurs, attendees will have the opportunity to discover and experience the newest tools and use-cases that are happening in the embedded AI world. We look forward to your virtual attendance!</p><style type="text/css" id="isPasted">p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 13.0px 'Helvetica Neue'}</style><p>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <a href="https://wevlv.co/imagineconf" target="_blank" rel="noopener noreferrer"><strong>REGISTER HERE</strong></a></p>

Edge AI

Latest Posts