Deep Learning
|
Engineer Recreates Google's TPU Chip Design on a $60 FPGA Using Systolic Arrays and Smart Approximation A YouTube creator running the channel "traffic in the brain" has published a detailed walkthrough of building a small-scale AI accelerator from scratch on a budget FPGA board, recreating the core architectural ideas behind Google's Tensor Processing Unit (TPU).
The project, released September 17, 2026, implements a two-layer attention model, the same… |
|
How MIT's Aerial Microrobots Fly as Agilely as Insects Engineers from MIT have developed aerial microrobots that are roughly 450% faster with about 250% better acceleration in comparison to prior demos. “We want to be able to use these robots in scenarios that more traditional quadcopter robots would have trouble flying into, but that insects could navigate,” said Kevin Chen, an associate professor at MIT. The robot's controller is… |
|
iRonCub3 Jet-Powered Humanoid Robot Achieves First Stable Flight A jet-powered humanoid robot named iRonCub3 just took its first flight. This robot, developed by the Italian Institute of Technology (IIT) in Genoa, lifted about 50 cm (1.5 feet) off the ground while maintaining stability. It has four engines, two on the arms and two on a jetpack on its back. This development follows years of research and testing that include real-world flight tests and… |
|
AI-Powered Smart Waste Sorting with VGG16, CSO and Random Forest Algorithm Sorting waste into the right categories, like plastic, glass, metal, or paper, is not as simple as it sounds. To make this tiresome job easier, researchers have developed a smart waste classification system that uses artificial intelligence to recognize different types of trash, making waste management easier and more efficient. A team of researchers from the Ronin Institute (USA), Asia… |
|
Advancing Robot Bikes with Reinforcement Learning The Robotics and AI (RAI) Institute has developed the Ultra Mobility Vehicle (UMV), a self-balancing robotic bike capable of navigating challenging terrain and even jumping onto high surfaces. Reinforcement learning (RL) is playing a key role in helping robots adapt to complex situations and perform better. Unlike traditional… |
|
Age and Gender Classification using OpenCV and Deep Learning on Raspberry Pi In this tutorial, we are going to use OpenCV and Deep Learning models to accurately identify the gender and age of a person from a real-time video stream. The deep learning age and gender detector model that we are going to use today was implemented and trained by Levi and Hassner in their 2015 publication. Age and Gender detection is a two-step process: … |
|
Renesas Updates R-Car V3H System-on-Chip (SoC) with Improved Deep Learning Performance to Meet Latest NCAP Requirements The popular R-Car V3H SoC with integrated IP for Convolutional Neural Networks (CNN) from Renesas Electronics Corporation has lately been updated with improved deep learning performance to meet NCAP 2020 requirements. The updated SoC combines sensor fusion on the real-time domain with up to ASIL C metrics and architecture optimized for smart computer vision. … |
|
High Precision, Low Power Smart Camera for Next-Generation ADAS The Renesas Electronics Corporation announced the joint development of a deep learning-based object recognition solution for smart cameras used in next-generation advanced driver assistance system applications and cameras for ADAS level 2 and above. This new smart camera solution employs deep learning for object recognition with high precision and low power consumption; it… |
