Lorem ipsum dolor sit amet, consectetur adicing elit ut ullamcorper. leo, eget euismod orci. Cum sociis natoque penati bus et magnis dis.Proin gravida nibh vel velit auctor aliquet. Leo, eget euismod orci. Cum sociis natoque penati bus et magnis dis.Proin gravida nibh vel velit auctor aliquet.

  /  Project   /  Blog: Whirring Engine of Machine Learning in a USB Stick

Blog: Whirring Engine of Machine Learning in a USB Stick

Intel NCS 2

Artificial Intelligence as a whole and Machine Learning in particular is growing exponentially as the days go by. One of the problems for developing machine learning models is computing power at the edge for developers. Devices are getting smaller and algorithms are becoming smarter. And who else to call out when you talk about devices? Why yes, Intel!

Intel hosted its first Artificial Intelligence developer conference to keep up with the growing trend in November 2018 at Beijing. Intel started the event with the introduction of the Intel Neural Compute Stick 2 designed to build smarter AI algorithms and for prototyping computer vision at the network edge. The Intel NCS 2 is based on the Intel Movidius Myriad X Vision Processing Unit (VPU) and supported by the Intel Distribution of OpenVINO toolkit. The Intel NCS 2 enables deep neural network testing, tuning, and prototyping, so developers can go from prototyping into production leveraging a range of Intel vision accelerator form factors in real-world applications.

AI on one side and Internet of Things (IoT) another lucrative and growing field of technology on the other side, the Intel NCS 2 enables developers to combine the power of both to harness the utility of the combined technology. The Myriad X VPU is the first to feature a neural compute engine — a dedicated hardware neural network inference accelerator delivering additional performance. Space, cost or thermal limitations prevent many edge devices to host bulky GPUs like the NVIDIA Jetson TX2. With a standard USB drive form factor, developers only need to connect the NCS 2 to a USB 3.0 port to deploy PC-trained models to a wide range of devices natively and without internet or cloud connectivity.

To get started with Intel NCS 2 is really simple. All you need is an x86–64 host computer with Windows 10 or Ubuntu 16.04 and internet connectivity to install the Intel® Distribution of OpenVINO toolkit. The Intel® Distribution of OpenVINO toolkit also supports the original Intel Movidius NCS device. Existing Intel Movidius Neural Compute SDK (NCSDK) projects can be transitioned to the Intel Distribution of OpenVINO toolkit. After running a few commands as here https://software.intel.com/en-us/articles/get-started-with-neural-compute-stick, you’ll be all set to use your Intel NCS 2.

Our team keeps on a lookout for technologies like these since we have to be at the cutting edge of technology at all times to do our best in the field of autonomous robotics and artificial intelligence.

Image Credit: Intel

Source: Artificial Intelligence on Medium

(Visited 4 times, 1 visits today)
Post a Comment