Graphics chipset-maker Nvidia has launched a tiny $99 artificial intelligence computer called Jetson Nano that can create multiple intelligent systems.
The company has also teamed up with Amazon Web Services to enable customers to deploy AI and deep learning to millions of connected devices, it said in a statement.
Powered by Nvidia's graphics processor unit (GPU) accelerating libraries for data science and AI (CUDA-X), the AI computer delivers 472 Gigaflops of computing performance for running AI workloads and consumes as little as 5 watts.
Jetson Nano comes in two versions—the $99 kit for developers, makers and enthusiasts, and the $129 production-ready module for companies looking to create mass-market edge systems.
“Jetson Nano makes AI more accessible to everyone—and is supported by the same underlying architecture and software that powers our nation’s supercomputers,” said Deepu Talla, vice president and general manager of autonomous machines at Nvidia.
The AI computer can run high-resolution sensors, can process many sensors in parallel and can run multiple modern neural networks on each sensor stream, Talla said. It also supports many popular AI frameworks, making it easy for developers to integrate their preferred models and frameworks into the product, he added.
Jetson Nano joins the Jetson AGX Xavier for fully autonomous machines and Jetson TX2 for AI at the edge.
The company also announced a collaboration with Andy Jassy-led AWS. This joint solution enables models to be easily created, trained and optimized on AWS, then deployed to Jetson-powered edge devices using AWS IoT Greengrass.
AWS IoT Greengrass extends AWS to edge devices so they can act locally on the data they generate while still using the cloud for management, analytics and durable storage. With AWS IoT Greengrass, connected devices can execute predictions based on machine learning models, keep device data in sync, and communicate with other devices securely – even when not connected to the Internet.
Applications of the collaboration will benefit projects such as autonomous machines and smart cameras for industries such as retail, manufacturing and agriculture.
The company also made a series of announcements for the automotive side of its business. It announced the general availability of its autonomous car simulation programme Drive Constellation and also entered into a partnership with Japanese automaker Toyota to develop, train and validate self-driving vehicles.
Drive Constellation is a data centre solution and is cloud-based. It enables millions of miles to be driven in virtual worlds across a broad range of scenarios — from routine driving to rare and dangerous situations — with greater efficiency, cost-effectiveness and safety than what is possible to achieve in the real world, the company said.