HaskellNN-0.1.3: High Performance Neural Network in Haskell

MaintainerKiet Lam <ktklam9@gmail.com>



Efficient representation of an Artificial Neural Network using vector to represent the weights between each layer

This module provides the neural network data representation that will be used extensively



data Network Source

The representation of an Artificial Neural Network




activation :: Double -> Double

The activation function for each neuron

derivative :: Double -> Double

The derivative of the activation function

lambda :: Double

The regularization constant

weights :: Vector Double

The vector of the weights between each layer of the neural network

architecture :: [Int]

The architecture of the neural networks.

e.g., a network of an architecture of 2-3-1 would have an architecture representation of [2,3,1]

NOTE: The library will automatically create a bias neuron in each layer, so you do not need to state them explicitly

toWeightMatrices :: Network -> [Matrix Double]Source

Get the list of matrices of weights between each layer. This can be more useful than the barebone vector representation of the weights