AI.HNN.Net
Contents
Description
Net module, defining functions to work on a neural network, which is a list of list of neurons
- check :: [[Neuron]] -> Bool
- nn :: [[Neuron]] -> [[Neuron]]
- computeNetU :: [[Neuron]] -> UArr Double -> UArr Double
- computeNet :: [[Neuron]] -> [Double] -> [Double]
- quadErrorNetU :: [[Neuron]] -> (UArr Double, UArr Double) -> Double
- quadErrorNet :: [[Neuron]] -> ([Double], [Double]) -> Double
- globalQuadErrorNetU :: [[Neuron]] -> [(UArr Double, UArr Double)] -> Double
- globalQuadErrorNet :: [[Neuron]] -> [([Double], [Double])] -> Double
- backPropU :: Double -> [[Neuron]] -> (UArr Double, UArr Double) -> [[Neuron]]
- backProp :: Double -> [[Neuron]] -> ([Double], [Double]) -> [[Neuron]]
- trainAux :: Double -> [[Neuron]] -> [(UArr Double, UArr Double)] -> [[Neuron]]
- trainU :: Double -> Double -> [[Neuron]] -> [(UArr Double, UArr Double)] -> [[Neuron]]
- train :: Double -> Double -> [[Neuron]] -> [([Double], [Double])] -> [[Neuron]]
Documentation
Computation
computeNetU :: [[Neuron]] -> UArr Double -> UArr DoubleSource
Computes the output of the given neural net on the given inputs
computeNet :: [[Neuron]] -> [Double] -> [Double]Source
Computes the output of the given neural net on the given inputs
Quadratic Error
quadErrorNetU :: [[Neuron]] -> (UArr Double, UArr Double) -> DoubleSource
Returns the quadratic error of the neural network on the given sample
quadErrorNet :: [[Neuron]] -> ([Double], [Double]) -> DoubleSource
Returns the quadratic error of the neural network on the given sample
globalQuadErrorNetU :: [[Neuron]] -> [(UArr Double, UArr Double)] -> DoubleSource
Returns the quadratic error of the neural network on the given samples
globalQuadErrorNet :: [[Neuron]] -> [([Double], [Double])] -> DoubleSource
Returns the quadratic error of the neural network on the given samples
Learning
backPropU :: Double -> [[Neuron]] -> (UArr Double, UArr Double) -> [[Neuron]]Source
Train the given neural network using the backpropagation algorithm on the given sample with the given learning ratio (alpha)
backProp :: Double -> [[Neuron]] -> ([Double], [Double]) -> [[Neuron]]Source
Train the given neural network using the backpropagation algorithm on the given sample with the given learning ratio (alpha)
trainU :: Double -> Double -> [[Neuron]] -> [(UArr Double, UArr Double)] -> [[Neuron]]Source
Train the given neural network on the given samples using the backpropagation algorithm using the given learning ratio (alpha) and the given desired maximal bound for the global quadratic error on the samples (epsilon)
train :: Double -> Double -> [[Neuron]] -> [([Double], [Double])] -> [[Neuron]]Source
Train the given neural network on the given samples using the backpropagation algorithm using the given learning ratio (alpha) and the given desired maximal bound for the global quadratic error on the samples (epsilon)