Jetson brought GPUGraphics processing unit — a chip optimized for parallel math; now used for graphics, ML, and scientific computing. compute to embedded robots, drones, and IoTInternet of Things — networked sensors and devices embedded in appliances, factories, and cities. gateways — developers ran TensorFlow and OpenCV on a $192 board with 192 CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation. cores. Later Jetson Nano, Xavier, and Orin modules powered production edge ML. It paired NVIDIA's CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation. ecosystem with maker-style single-board hardware.

Jetson TK1 was NVIDIA's first CUDANVIDIA's parallel computing platform — lets developers run general code on GPUs for ML and simulation.-capable embedded developer board.

It made GPUGraphics processing unit — a chip optimized for parallel math; now used for graphics, ML, and scientific computing.-accelerated inferenceRunning a trained model to produce predictions — as opposed to the training phase that learns weights. practical on edge devices outside datacenters.