Neural compute stick delivers smarter AI algorithms

22nd January 2019

Rutronik

Mick Elliott

0 0

The Neural Compute Stick 2 (NCS2) from Intel is designed to build smarter AI algorithms and for prototyping computer vision at the network edge. It affordably speeds the development of deep neural networks inference applications while delivering a performance boost over the previous generation neural compute stick. The NCS2 is available immediately on www.Rutronik24.com.

The Intel NCS 2 is powered by the latest generation of Intel VPU (vision processing unit) – the Intel Movidius Myriad X VPU. This is the first VPU that features a neural compute engine for delivering additional performance.

Deep Learning Neural Networks like Caffe, Tensor Flow or MXNet can be integrated with the OpenVINO toolkit on the NCS2.

These machine learning frameworks are optimised for the entirely new Deep Neural Network (DNN) inferencing engine, which delivers eight times the performance of the previous generation.

With a laptop and the Intel NCS2, developers can have their AI and computer vision applications up and running in minutes.

The Intel NCS2 runs on a standard USB 3.0 port and requires no additional hardware, enabling users to seamlessly convert and then deploy PC-trained models to a wide range of devices and without internet or cloud connectivity.

Whether developing a smart camera, a drone with gesture-recognition capabilities, an industrial robot, or the next, smart home device, the Intel Neural Compute Stick 2 offers what developers need to prototype faster.