The neural package

[maintain]

The goal of neural is to provide a modular and flexible neural network library written in native Haskell.

Features include

The idea is to be able to easily define new components and wire them up in flexible, possibly complicated ways (convolutional deep networks etc.).

Three examples are included as proof of concept:

The library is still very much experimental at this point.


[Skip to ReadMe]

Properties

Versions0.1.0.0, 0.1.0.1, 0.1.1.0, 0.2.0.0, 0.2.0.0, 0.3.0.0
Dependenciesad (>=4.3.2 && <4.4), array (>=0.5.1.0 && <0.6), attoparsec (>=0.13.0.1 && <0.14), base (>=4.7 && <5), bytestring (>=0.10.6.0 && <0.11), deepseq (>=1.4.1.1 && <1.5), directory (>=1.2.2.0 && <1.3), filepath (>=1.4.0.0 && <1.5), ghc-typelits-natnormalise (>=0.4.1 && <0.5), hspec (>=2.2.2 && <2.3), JuicyPixels (>=3.2.7 && <3.3), kan-extensions (>=4.2.3 && <4.3), lens (==4.13.*), monad-par (>=0.3.4.7 && <0.4), monad-par-extras (>=0.3.3 && <0.4), MonadRandom (>=0.4.2.2 && <0.5), mtl (>=2.2.1 && <2.3), neural (>=0.2.0.0 && <0.3), parallel (>=3.2.1.0 && <3.3), pipes (>=4.1.8 && <4.2), pipes-bytestring (>=2.1.1 && <2.2), pipes-safe (>=2.2.3 && <2.3), pipes-zlib (>=0.4.4 && <0.5), profunctors (==5.2.*), reflection (>=2.1.2 && <2.2), STMonadTrans (>=0.3.3 && <0.4), text (>=1.2.2.1 && <1.3), transformers (>=0.4.2.0 && <0.5), typelits-witnesses (>=0.2.0.0 && <0.3), vector (>=0.11.0.0 && <0.12) [details]
LicenseMIT
CopyrightCopyright: (c) 2016 Lars Bruenjes
AuthorLars Bruenjes
Maintainerbrunjlar@gmail.com
Stabilityprovisional
CategoryMachine Learning
Home pagehttps://github.com/brunjlar/neural
Bug trackerhttps://github.com/brunjlar/neural/issues
Source repositoryhead: git clone https://github.com/brunjlar/neural.git
this: git clone https://github.com/brunjlar/neural.git(tag 0.1.1.0)
ExecutablesMNIST, sqrt, iris
UploadedWed Jun 15 23:51:50 UTC 2016 by lbrunjes

Modules

Downloads

Maintainers' corner

For package maintainers and hackage trustees

Readme for neural-0.2.0.0

neural - Neural Nets in native Haskell

Build Status

Motivation

The goal of this project is to provide a flexible framework for neural networks (and similar parameterized models) in Haskell. There are already a couple of neural network libraries out there on Hackage, but as far as I can tell, they either

Examples

At the moment, three examples are included: