Intel and facebook have come out with the Nervana chip that brings AI/ML within reach of everyone by building not just a chip, but an ecosystem designed to work in conjunction with the chip. It will be interesting to see how this approach works out and if it can increase the penetration of AI/ML at sharply reduced cost. Any thoughts or opinions on this appreciated. Will this become a template for future AI/ML systems. Will the heavy lifting be split between a cheaper chip and the data center as a way of lowering costs?

Cheaper AI for everyone is the promise with Intel and Facebook’s new chip - MIT Technology Review