Incredible. Given a (one-to-one) Julia function `f`, this package generates `~f`, the inverse of f. Clever use of automatic differentiation.<p>Paper: <a href="https://arxiv.org/abs/2003.04617" rel="nofollow">https://arxiv.org/abs/2003.04617</a>
,,The performance of reversible programming automatic differentiation is much better than most traditional frameworks.''<p>It would be good to see a ResNet training benchmark comparison with PyTorch as an example if this is really true.
This is the latest NiLang tutorial notebook: <a href="https://github.com/JuliaReverse/NiLangTutorial" rel="nofollow">https://github.com/JuliaReverse/NiLangTutorial</a>