Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Great question. Both TensorFlow and PyTorch pretty much do nothing https://github.com/tensorflow/tensorflow/issues/20524


That seems strange, if I'm reading it correctly.

In the author's packages, integers which label dimensions etc. have gradient `nothing`, but arrays which happen to contain integers do not signal anything:

    julia> Zygote.gradient((x,d)->abs(sum(sin,fft(x,d))), [2 2; 0 0], 2)
    (Complex{Float64}[-0.346356+0.0im 1.65364+0.0im; -2.0+0.0im 0.0+0.0im], nothing)


It is possible to do backprop with integers: https://arxiv.org/abs/1802.04680




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: