Live data from Hacker News

Towards Acceleration of Deep Convolutional Neural Networks [pdf]

zheli0416.com

1–3 of 3 posts

Re: Towards Acceleration of Deep Convolutional Neural Networks [pdf]

#3
2.86% accuracy drop on MNIST is massive. This accuracy could be achieved with dramatically simpler algorithms. We use neural networks because they are more accurate, so if you take that away there is no point.

Also, they didn't actually build any hardware, they only ran some simulations.