[Haskell-cafe] Accelerating Automatic Differentiation

Tom Ellis tom-lists-haskell-cafe-2013 at jaguarpaw.co.uk
Thu Mar 29 23:41:43 UTC 2018


On Sun, Mar 25, 2018 at 11:57:53PM +0000, Trevor McDonell wrote:
> Regarding TensorFlow (and PyTorch, etc), it is important to note that TF is
> designed specifically for the deep-learning style of machine learning, but
> automatic differentiation itself is a much more generally useful and finds
> applications in physics, finance, optimisation... not just machine
> learning.

It's true that TF and PyTorch are designed for deep learning applications
but is there really anything presenting one using them for the other
applications you mention?


More information about the Haskell-Cafe mailing list