The MIT is preparing a new chip architecture inspired by Neural Networks. It aims at replacing GPUs on mobile devices.
GPUs are typically used to process Deep Learning algorithms. Contrarily to CPUs, which are specialised in sequential complex computations, GPUs’ multiple small cores allows them to compute each layer of the neural networks more efficiently. MIT’s new chip is even more tailored for such tasks, increasing computational and power efficiency.
If such investment is now made on hardware, no wonder what’s the future of machine learning algorithms!