Featured
Columbia Engineering researchers use AI to teach robots to make appropriate reactive human facial expressions, an ability that could build trust between humans and their robotic co-workers and care-givers
Be the first to know.
Get our Computer Vision weekly email digest.
Computer Vision
featured
Columbia Engineering researchers use AI to teach robots to make appropriate reactive human facial expressions, an ability that could build trust between humans and their robotic co-workers and care-givers
Featured
Engineers at EPFL have developed a predictive control model that allows swarms of drones to fly in cluttered environments quickly and safely. It works by enabling individual drones to predict their own behavior and that of their neighbors in the swarm.
Featured
Cobots when combined with Artificial Intelligence(AI), can effectively work alongside humans in the real world on their daily tasks. With an AI technique called Inverse Reinforcement learning (IRL), the robot can observe a human performing the task and learn how to do it quite intuitively.
Engineers Wiki. Most Asked Questions.
This article explores TPU vs GPU differences in architecture, performance, energy efficiency, cost, and practical implementation, helping engineers and designers choose the right accelerator for AI workloads today!
TPU vs GPU: Comprehensive Technical Comparison
By Umar Waseem.
14 minutes read.
NPU vs GPU: Understanding the Key Differences and Use Cases
By Ravi Rao.
13 minutes read.
RAG vs Fine-Tuning: Differences, Benefits, and Use Cases Explained
By Ravi Rao.
18 minutes read.
LLM Training: Mastering the Art of Language Model Development
By Ravi Rao.
30 minutes read.
ORGANIZATIONS. SHAPING THE INDUSTRY.
High Tech Campus Eindhoven
High Tech
High Tech Campus Eindhoven is Europe's smartest square km and has the ultim...
49 Posts
ETH Zurich
University for science and technology
Freedom and individual responsibility, entrepreneurial spirit and open-min...
43 Posts
TAGGED WITH machine learning
Training AI models is costly, forcing a trade-off between compressing large models or accepting weaker performance from smaller ones trained from scratch.
This new approach adapts to decide which robots should get the right of way at every moment, avoiding congestion and increasing throughput.
A team that included Chongzie Zhang from McKelvey Engineering developed a method that allows robots to teach other robots with different features to perform the same task.
New AI system lets robots work faster than their human teachers without sacrificing accuracy.
TAGGED WITH motion capture systems
with Xsens motion capture
Latest Posts
Columbia Engineering researchers use AI to teach robots to make appropriate reactive human facial expressions, an ability that could build trust between humans and their robotic co-workers and care-givers
Engineers at EPFL have developed a predictive control model that allows swarms of drones to fly in cluttered environments quickly and safely. It works by enabling individual drones to predict their own behavior and that of their neighbors in the swarm.
2 minutes read
Cobots when combined with Artificial Intelligence(AI), can effectively work alongside humans in the real world on their daily tasks. With an AI technique called Inverse Reinforcement learning (IRL), the robot can observe a human performing the task and learn how to do it quite intuitively.
3 minutes read
There are two ways to mount a 3D vision system in the robotic cell, each having its advantages and each being more suitable for certain applications. However, there are many cases where hand-eye calibration surpasses the more traditional setup in a number of respects.
4 minutes read
Fewer typing errors when touching a smartphone keyboard: ETH Computer scientists have developed a new AI solution that enables touchscreens to sense with eight times higher resolution than current devices. Thanks to AI, their solution can infer much more precisely where fingers touch the screen.
4 minutes read
In the agri-food sector, the range of treats has been growing for a long time: sweet snacks, chocolate spreads and pastries are becoming more popular all over the world. To produce these delicacies, different kinds of shell nuts are necessary, such as walnuts, almonds, hazelnuts and macadamia nuts.
4 minutes read
Theory-based residual neural network combines discrete choice models and deep neural networks, long viewed as conflicting methods.
with Xsens MTi
4 minutes read
The customer decided to automate the process of picking 6 different types of pipe parts from a bin and placing them into a swedging machine. The solution consists of a Staübli TX2-90L robot equipped with a Photoneo PhoXi 3D Scanner.
From Single Models to Full MLOps, Edge Impulse Is The New Instruction Engine For A Smarter Industrial Sector.
Over the past few months, you’ve may have heard talk about TinyML: the idea of running machine learning models on microcontrollers, and other small devices that don’t use much power.
5 minutes read
Brian de Bart, Team Lead Automotive System Innovation at NXP explains about chips and AI in automotive industry as part of a series from the founding partners of the AI Innovation Center at High Tech Campus Eindhoven.
5 minutes read
Arnaud Hubaux, Senior Technical Program Manager explains about optimization of ASML machines as part of a series from the founding partners of the AI Innovation Center at High Tech Campus Eindhoven.
5 minutes read
Interesting discussion with Hod Lipson, the head of Creative Machines Lab, Columbia University in New York. In this episode, Can robots be Self-aware? Can robots design other robots and self-repair? Why should we evolve robots to do tasks that animals do so well?
You can now build tiny machine learning (TinyML) models that interpret sensor data in realtime, from detecting lions roaring to tracking sheep workouts.