Personal tools

HNN

From HaskellWiki

Revision as of 19:00, 5 January 2010 by Henk-Jan van Tuyl (Talk | contribs)

Jump to: navigation, search


Contents

1 Description

HNN (stands for Haskell Neural Network library) is an attempt at providing a simple but powerful and efficient library to deal with feed-forward neural networks in Haskell.

2 Why another neural network library ?

I tried HFANN and few other code I found before deciding to write my own library. But I wasn't satisfied with them. They are more comprehensive but they were not to be used the way I intended to, for a Haskell neural network library. Mine is much simpler, less comprehensive but is an attempt at easily creating, training and using neural networks in Haskell, without performance losses. Note : HNN is full-Haskell unlike HFANN which is a binding to a C library.

3 Get the code

3.1 From Hackage

hnn-0.1 is on Hackage, in the AI category. A simple :

  • cabal install hnn

should install HNN for you. (You may need to do a cabal update before so that cabal will be aware of the new package named hnn -- and of course of the other new packages or new versions of the packages)


3.2 From the git repository

HNN is hosted on github : [1] The instructions to get it and build it are :

After these commands, provided you have ghc 6.8 or later and the 'uvector' package installed, HNN will be installed just like any other library. To generate the documentation, you have to execute :

  • cabal haddock

or you can just pass the --enable-documentation flag to cabal install. The documentation should then be in HNN/dist/doc/.

You can see the xor-3input.hs file for an example of use of the library (see HNN#Example on this page).

4 Documentation

There is an online version of the documentation here : [2] but there should be the same doc soon on the hackage page of hnn.

5 Example

Here is a simple example of use of the HNN library.

xor-3inputs.hs file :

module Main where
 
import AI.HNN.Net
import AI.HNN.Layer
import AI.HNN.Neuron
import Data.Array.Vector
import Control.Arrow
import Data.List
 
alpha = 0.8 :: Double -- learning ratio
epsilon = 0.001 :: Double -- desired maximal bound for the quad error
 
layer1, layer2 :: [Neuron]
 
layer1 = createSigmoidLayer 4 0.5 [0.5, 0.5, 0.5] -- the hidden layer
 
layer2 = createSigmoidLayer 1 0.5 [0.5, 0.4, 0.6, 0.3] -- the output layer
 
net = [layer1, layer2] -- the neural network
 
finalnet = train alpha epsilon net [([1, 1, 1],[0]), ([1, 0, 1],[1]), ([1, 1, 0],[1]), ([1, 0, 0],[0])] -- the trained neural network
 
good111 = computeNet finalnet [1, 1, 1]
good101 = computeNet finalnet [1, 0, 1]
good110 = computeNet finalnet [1, 1, 0]
good100 = computeNet finalnet [1, 0, 0]
 
main = do
     putStrLn $ "Final neural network : \n" ++ show finalnet
     putStrLn " ---- "
     putStrLn $ "Output for [1, 1, 1] (~ 0): " ++ show good111
     putStrLn $ "Output for [1, 0, 1] (~ 1): " ++ show good101
     putStrLn $ "Output for [1, 1, 0] (~ 1): " ++ show good110
     putStrLn $ "Output for [1, 0, 0] (~ 0): " ++ show good100

Compile it with ghc -O2 --make xor-3inputs.hs -o xor-3 and launch it. You should get something close to the following.


$ ./xor-3inputs 
Final neural network : 
[[Threshold : 0.5
Weights : toU [1.30887603787326,1.7689534867644316,2.2908214981696453],Threshold : 0.5
Weights : toU [-2.4792430791673947,4.6447786039112655,-4.932860802255383],Threshold : 0.5
Weights : toU [2.613377735822592,6.793687725768354,-5.324081206358496],Threshold : 0.5
Weights : toU [-2.5134194114492585,4.730152273922408,-5.021321916827272]],[Threshold : 0.5
Weights : toU [4.525235803191061,4.994126671590998,-8.2102354168462,5.147655509585701]]]
 ---- 
Output for [1, 1, 1] (~ 0): [2.5784449476436315e-2]
Output for [1, 0, 1] (~ 1): [0.9711209812630944]
Output for [1, 1, 0] (~ 1): [0.9830499812666017]
Output for [1, 0, 0] (~ 0): [1.4605247804272069e-2]

6 Feedback, participation and all

If you have anything to say related to the HNN library, please send an email to alpmestan <a t> gmail <d o t> com. I'd be pleased to hear from any HNN user so don't hesitate ! Thank you.