Closed jiweiqi closed 3 years ago
https://diffeqflux.sciml.ai/dev/controlling_AD/#
Useful introduction https://www.dianacai.com/blog/2020/04/13/machine-learning-julia-flux-autodiff/
Use pullback to return both loss and its gradient https://fluxml.ai/Zygote.jl/dev/adjoints/
https://diffeqflux.sciml.ai/dev/controlling_AD/#