Collaborating Authors


Vision Processing Units (VPUs)


On my first day working for MILLA, an autonomous shuttle company, I discovered a shuttle that can drive up to 30 km/h; quite an improvement if you compare it to our competitors at the time driving at 5–8 km/h. At the time, the shuttle was new and there was no GPU yet on it. In case you don't know what a GPU is, here's a quick picture that explains it well: A GPU (Graphic Processing Unit) parallels the processes so operations are done faster. In a self-driving car, this can be super useful for computer vision or point cloud processing. It was first released in video games because of the need to display multiple things at the same time.

Raspberry Pi with a side of AI: These powerful new boards come with NPUs


Video: How to set up your Raspberry Pi 3 Model B . The Raspberry Pi Foundation just released the Raspberry Pi 3 Model B with a zippier CPU and faster network connections, but what the hugely popular $35 board hasn't yet gained is a neural processing unit (NPU). NPUs are helping manufacturers of lesser-known boards speed up computer-vision applications, such as image and object recognition, and offer enterprise and manufacturers a more powerful platform for building everything from smart building applications to autonomous vehicles. The new boards have dedicated NPUs from Huawei and Rockchip. The Rock960 meanwhile comes with Rockchip's souped-up RK 3399Pro, a processor that target's Google's TensorFlow Lite framework for building AI services on iOS and Android devices.