H/T: Engadget
The NVIDIA Jetson Nano just might be the most affordable AI computer yet, thanks to its CUDA-X AI computer that delivers 472 GFLOPS of compute performance for running modern artificial intelligence workloads, while also being highly power-efficient, consuming as little as 5 watts. It supports high-resolution sensors, can process many sensors in parallel and run multiple modern neural networks on each sensor stream. Read more to see how computer science grad students Jason Stock and Tom Cavey used it to reward good dogs.
Simply put, they trained the NVIDIA Jetson Edge AI with over 20,000 labeled images of dogs in various positions. Next, the AI was capable of recognizing Henry, Cavey’s Australian Shepherd, with up to 92% accuracy at 39 frames per second, rewarding it with a treat via servo motor when the right position is followed. Eventually, the duo hopes to use this system as a teaching aid, enabling dogs to be remotely trained.
- Powered by the NVIDIA Blackwell architecture and DLSS 4
- Military-grade components deliver rock-solid power and longer lifespan for ultimate durability
- Protective PCB coating helps protect against short circuits caused by moisture, dust, or debris
Jetson Nano makes AI more accessible to everyone — and is supported by the same underlying architecture and software that powers our nation’s supercomputers. Bringing AI to the maker movement opens up a whole new world of innovation, inspiring people to create the next big thing,” said Deepu Talla, vice president and general manager of Autonomous Machines at NVIDIA.
