BottleFit framework applied DNN models in image classification achieves 77.1% data compression with up to 0.6% accuracy loss on the ImageNet dataset.
Be the first to know.
Get our machine learning weekly email digest.
Tagged with
machine learning
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
University of Michigan
Higher Education
Work together. Create smart machines. Serve society. University of Michiga...
40 Posts
View more
Latest Posts
In this article, we look at two tinyML projects for education. We show how Backyard Brains uses low-cost experiment kits to make neuroscience education more accessible. We also introduce our readers to a specialisation offered by Harvard & Google to help students learn tinyML like never before.
Considered obsolete since the introduction of vision transformers, ConvNeXt proves there's life in convolution yet — outperforming its rivals by adopting some of their own tricks.
A holistic open-source framework to improve the performance of multiple modalities and outperform the existing single-modality algorithms.
ETH researchers led by Marco Hutter developed a new control approach that enables a legged robot, called ANYmal, to move quickly and robustly over difficult terrain. Thanks to machine learning, the robot can combine its visual perception of the environment with its sense of touch for the first time.
3 minutes read
In this article, we take a look at two tinyML projects related to healthcare. The first project helps gather Mean Radiant Temperature data outdoors to protect people from extreme heat, and the other one is a solution for affordable, accurate, & rapid detection of pneumonia.
Removing litter from oceans and seas is a costly and time-consuming process. As part of a European cooperative project, a team at the Technical University of Munich (TUM) is developing a robotic system that uses machine learning methods to locate and collect waste under water.
Ultra-precise lasers can be used for optical atomic clocks, quantum computers, power cable monitoring, and much more. But all lasers make noise, which researchers from DTU Fotonik want to minimize using machine learning.
4 minutes read
At READY we want to engage the landscape of developers outside the robotics industry to be programmers in the robotics industry.
4 minutes read
In this episode, we talk about how a breakthrough with compact laser nano-printers can make them more accessible for researchers and how leveraging 3D printing technology and machine learning will provide essential insight for developing next-gen cochlear implants.
In this article, we take a look at two tinyML projects that have the potential to make contributions towards sustainable development goals. While the first project is about revolutionising precision farming, the second one aims to create a network of low-cost sensors for mapping carbon emissions.
Edge Impulse recently announced official support for the Syntiant NDP101 processor, an always-on sensor and speech recognition processor, with ultra-low power consumption of less than 140 uW while recognizing words.
In this episode, we talk about how computer vision works and discuss an application coming out of the Technical University of Denmark that can help dairy farmers remove weeds from their fields.
Learn how vision AI can be used to prevent damage and contamination by detecting unwanted material during processing and manufacturing.
3 minutes read
The collaboration between Nordic Semiconductor and Edge Impulse provides resource-optimized IoT devices with more accessible machine learning at the edge.
3 minutes read
