grenade

Practical Deep Learning in Haskell

Latest on Hackage:0.1.0

This package is not currently in any snapshots. If you're interested in using it, we recommend adding it to Stackage Nightly. Doing so will make builds more reliable, and allow stackage.org to host generated Haddocks.

BSD-2-Clause licensed and maintained by Huw Campbell

Grenade is a composable, dependently typed, practical, and fast recurrent neural network library for precise specifications and complex deep neural networks in Haskell.

Grenade provides an API for composing layers of a neural network into a sequence parallel graph in a type safe manner; running networks with reverse automatic differentiation to calculate their gradients; and applying gradient decent for learning.

Documentation and examples are available on github https://github.com/HuwCampbell/grenade.