Tutorial: DeepMind's Synthetic Gradients Posted by iamtrask on March 21, 2017 TLDR: In this blogpost, we're going to prototype (from scratch) and learn the intuitions behind DeepMind's recently proposed Decoupled Neural Interfaces Using Synthetic Gradients paper. I typically tweet out new blogposts when they're complete at @iamtrask. Feel free to follow if you'd be interested in reading more in th
![Deep Learning without Backpropagation - i am trask](https://cdn-ak-scissors.b.st-hatena.com/image/square/11aa47bc191afb216201d3baa8fc9b85fa9467fb/height=288;version=1;width=512/https%3A%2F%2Fiamtrask.github.io%2Fimg%2Fsynthetic_grads_paper.png)