Tweeted By @hardmaru
The JAX Autodiff Cookbook
— hardmaru (@hardmaru) March 14, 2019
JAX's autodiff is very general. It can calculate gradients of numpy functions, differentiating them with respect to nested lists, tuples and dicts. It can also calculate gradients of gradients and even work with complex numbers!https://t.co/J4jz6cTFlI pic.twitter.com/jcGUtlbzJf