neural-0.3.0.1: neural.cabal
name: neural
version: 0.3.0.1
synopsis: Neural Networks in native Haskell
description:
The goal of `neural` is to provide a modular and flexible neural network library written in native Haskell.
.
Features include
.
* /composability/ via arrow-like instances and
<https://hackage.haskell.org/package/pipes pipes>,
.
* /automatic differentiation/ for automatic gradient descent/ backpropagation training
(using Edward Kmett's fabulous <https://hackage.haskell.org/package/ad ad> library).
.
The idea is to be able to easily define new components and wire them up in flexible, possibly
complicated ways (convolutional deep networks etc.).
.
Four examples are included as proof of concept:
.
* A simple neural network that approximates the sine function on [0,2 pi].
.
* Another simple neural network that approximates the sqrt function on [0,4].
.
* A slightly more complicated neural network that solves the famous
<https://en.wikipedia.org/wiki/Iris_flower_data_set Iris flower> problem.
.
* A first (still simple) neural network for recognizing handwritten digits from the equally famous
<https://en.wikipedia.org/wiki/MNIST_database MNIST> database.
.
The library is still very much experimental at this point.
extra-source-files:
.travis.yml
.gitignore
.ghci
stack.yaml
README.markdown
homepage: https://github.com/brunjlar/neural
bug-reports: https://github.com/brunjlar/neural/issues
license: MIT
license-file: LICENSE
author: Lars Bruenjes
maintainer: brunjlar@gmail.com
copyright: Copyright: (c) 2016 Lars Bruenjes
category: Machine Learning
build-type: Simple
cabal-version: >=1.10
stability: provisional
tested-with: GHC == 7.10.3, GHC == 8.0.1, GHC == 8.0.2
library
hs-source-dirs: src
exposed-modules: Numeric.Neural
, Numeric.Neural.Convolution
, Numeric.Neural.Layer
, Numeric.Neural.Model
, Numeric.Neural.Normalization
, Numeric.Neural.Pipes
, Data.FixedSize
, Data.FixedSize.Class
, Data.FixedSize.Matrix
, Data.FixedSize.Vector
, Data.FixedSize.Volume
, Data.MyPrelude
, Data.Utils
, Data.Utils.Analytic
, Data.Utils.Arrow
, Data.Utils.Cache
, Data.Utils.List
, Data.Utils.Pipes
, Data.Utils.Random
, Data.Utils.Stack
, Data.Utils.Statistics
, Data.Utils.Traversable
other-modules:
ghc-options: -Wall -fexcess-precision -optc-O3 -optc-ffast-math
build-depends: base >= 4.7 && < 5
, ad
, array
, bytestring
, containers
, deepseq
, directory
, filepath
, ghc-typelits-natnormalise
, hspec
, kan-extensions
, lens
, MonadRandom
, monad-par
, monad-par-extras
, mtl
, parallel
, pipes
, pipes-bytestring
, pipes-safe
, profunctors
, random
, reflection
, STMonadTrans
, text
, transformers
, typelits-witnesses
, vector
, vector-sized
default-language: Haskell2010
test-suite neural-test
type: exitcode-stdio-1.0
hs-source-dirs: test
main-is: Spec.hs
build-depends: base >= 4.7 && < 5
, hspec
, MonadRandom
, neural
other-modules: Data.Utils.CacheSpec
, Data.FixedSize.ClassSpec
, Data.FixedSize.MatrixSpec
, Data.FixedSize.VectorSpec
, Data.FixedSize.VolumeSpec
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
test-suite neural-doctest
type: exitcode-stdio-1.0
hs-source-dirs: doctest
main-is: doctest.hs
build-depends: base >= 4.7 && < 5
, doctest
, Glob
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
benchmark neural-bench
type: exitcode-stdio-1.0
hs-source-dirs: benchmark
main-is: benchmark.hs
build-depends: base >= 4.7 && < 5
, criterion
, neural
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
executable iris
hs-source-dirs: examples/iris
main-is: iris.hs
build-depends: base >= 4.7 && < 5
, attoparsec
, neural
, text
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
executable sin
hs-source-dirs: examples/sin
main-is: sin.hs
other-modules: Graph
build-depends: base >= 4.7 && < 5
, ansi-terminal
, array
, neural
, MonadRandom
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
executable sqrt
hs-source-dirs: examples/sqrt
main-is: sqrt.hs
build-depends: base >= 4.7 && < 5
, MonadRandom
, neural
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
executable MNIST
hs-source-dirs: examples/MNIST
main-is: MNIST.hs
build-depends: base >= 4.7 && < 5
, array
, JuicyPixels
, neural
, pipes
, pipes-zlib
ghc-options: -Wall -threaded -rtsopts -with-rtsopts=-N -fexcess-precision -optc-O3 -optc-ffast-math
default-language: Haskell2010
source-repository head
type: git
location: https://github.com/brunjlar/neural.git
source-repository this
type: git
location: https://github.com/brunjlar/neural.git
tag: 0.3.0.1