private static void Train()
{
Console.WriteLine("Network Training");
PrintUnderline(50);
Console.WriteLine("\t1. Train to minimum error");
Console.WriteLine("\t2. Train to max epoch");
Console.WriteLine("\t3. Network Menu");
PrintNewLine();
//BackPropTrainParams trainParams = null;
BackPropLearning learning = null;
switch (GetInput("\tYour Choice: ", 1, 3))
{
case 1:
var minError = GetDouble("\tMinimum Error: ", 0.000000001, 1.0);
PrintNewLine();
Console.WriteLine("\tTraining...");
//trainParams = new BackPropTrainParams { Training = TrainingType.MinimumError, MinimumError = minError };
learning = new BackPropLearning(_network)
{
MinimumError = minError
};
learning.TrainByError(_dataSets);
//_network.Train(_dataSets, trainParams);
Console.WriteLine("\t**Training Complete**");
PrintNewLine();
NetworkMenu();
break;
case 2:
var maxEpoch = GetInput("\tMax Epoch: ", 1, int.MaxValue);
if (!maxEpoch.HasValue)
{
PrintNewLine();
NetworkMenu();
return;
}
PrintNewLine();
Console.WriteLine("\tTraining...");
learning = new BackPropLearning(_network)
{
NumEpochs = maxEpoch.Value
};
learning.TrainByEpochs(_dataSets);
Console.WriteLine("\t**Training Complete**");
PrintNewLine();
break;
case 3:
NetworkMenu();
break;
}
PrintNewLine();
}
public void BackPropRationalSigmoidXorTest()
{
var nnet = new Network(2, new int[] { 2 }, 1, typeof(RationalSigmoid), typeof(RationalSigmoid));
var learning = new BackPropLearning(nnet)
{
MinimumError = 0.1,
Momentum = 0.5,
LearnRate = 0.1
};
learning.TrainByError(BuildXorDataSets(), 20000);
System.Diagnostics.Debug.WriteLine("trained in {0} epochs", learning.ResultEpochs);
CheckResults(nnet, 0.15);
}
static void Main(string[] args)
{
_network = new NeuronNet(2, 3, 1);
var learning = new BackPropLearning(_network);
var param = new BackPropParams()
{
CallBack = cb,
Eta = 0.9,
Alpha = 0.05,
ErrorStopValue = 0.05
};
learning.TrainNetworkBySample(XorSamples, XorSamples, param);
//learning.TrainNetworkByBatch(XorSamples, XorSamples, param);
//var param2 = new RPropParams();
//var learning2 = new RPropLearning(_network);
//learning2.Train(XorSamples, XorSamples, param2);
Console.WriteLine("press enter...");
Console.ReadLine();
}
public void testWeightsAndBiasesUpdatedCorrectly()
{
Matrix weightMatrix1 = new Matrix(2, 1);
weightMatrix1.set(0, 0, -0.27);
weightMatrix1.set(1, 0, -0.41);
Vector biasVector1 = new Vector(2);
biasVector1.setValue(0, -0.48);
biasVector1.setValue(1, -0.13);
Layer layer1 = new Layer(weightMatrix1, biasVector1,
new LogSigActivationFunction());
LayerSensitivity layer1Sensitivity = new LayerSensitivity(layer1);
Vector inputVector1 = new Vector(1);
inputVector1.setValue(0, 1);
layer1.feedForward(inputVector1);
Matrix weightMatrix2 = new Matrix(1, 2);
weightMatrix2.set(0, 0, 0.09);
weightMatrix2.set(0, 1, -0.17);
Vector biasVector2 = new Vector(1);
biasVector2.setValue(0, 0.48);
Layer layer2 = new Layer(weightMatrix2, biasVector2,
new PureLinearActivationFunction());
Vector inputVector2 = layer1.getLastActivationValues();
layer2.feedForward(inputVector2);
Vector errorVector = new Vector(1);
errorVector.setValue(0, 1.261);
LayerSensitivity layer2Sensitivity = new LayerSensitivity(layer2);
layer2Sensitivity.sensitivityMatrixFromErrorMatrix(errorVector);
layer1Sensitivity
.sensitivityMatrixFromSucceedingLayer(layer2Sensitivity);
BackPropLearning.calculateWeightUpdates(layer2Sensitivity, layer1
.getLastActivationValues(), 0.1);
BackPropLearning.calculateBiasUpdates(layer2Sensitivity, 0.1);
BackPropLearning.calculateWeightUpdates(layer1Sensitivity,
inputVector1, 0.1);
BackPropLearning.calculateBiasUpdates(layer1Sensitivity, 0.1);
layer2.updateWeights();
Matrix newWeightMatrix2 = layer2.getWeightMatrix();
Assert.AreEqual(0.171, newWeightMatrix2.get(0, 0), 0.001);
Assert.AreEqual(-0.0772, newWeightMatrix2.get(0, 1), 0.001);
layer2.updateBiases();
Vector newBiasVector2 = layer2.getBiasVector();
Assert.AreEqual(0.7322, newBiasVector2.getValue(0), 0.00001);
layer1.updateWeights();
Matrix newWeightMatrix1 = layer1.getWeightMatrix();
Assert.AreEqual(-0.265, newWeightMatrix1.get(0, 0), 0.001);
Assert.AreEqual(-0.419, newWeightMatrix1.get(1, 0), 0.001);
layer1.updateBiases();
Vector newBiasVector1 = layer1.getBiasVector();
Assert.AreEqual(-0.475, newBiasVector1.getValue(0), 0.001);
Assert.AreEqual(-0.139, newBiasVector1.getValue(1), 0.001);
}
public void testBiasUpdateMatrixesFormedCorrectly()
{
Matrix weightMatrix1 = new Matrix(2, 1);
weightMatrix1.set(0, 0, -0.27);
weightMatrix1.set(1, 0, -0.41);
Vector biasVector1 = new Vector(2);
biasVector1.setValue(0, -0.48);
biasVector1.setValue(1, -0.13);
Layer layer1 = new Layer(weightMatrix1, biasVector1,
new LogSigActivationFunction());
LayerSensitivity layer1Sensitivity = new LayerSensitivity(layer1);
Vector inputVector1 = new Vector(1);
inputVector1.setValue(0, 1);
layer1.feedForward(inputVector1);
Matrix weightMatrix2 = new Matrix(1, 2);
weightMatrix2.set(0, 0, 0.09);
weightMatrix2.set(0, 1, -0.17);
Vector biasVector2 = new Vector(1);
biasVector2.setValue(0, 0.48);
Layer layer2 = new Layer(weightMatrix2, biasVector2,
new PureLinearActivationFunction());
LayerSensitivity layer2Sensitivity = new LayerSensitivity(layer2);
Vector inputVector2 = layer1.getLastActivationValues();
layer2.feedForward(inputVector2);
Vector errorVector = new Vector(1);
errorVector.setValue(0, 1.261);
layer2Sensitivity.sensitivityMatrixFromErrorMatrix(errorVector);
layer1Sensitivity
.sensitivityMatrixFromSucceedingLayer(layer2Sensitivity);
Vector biasUpdateVector2 = BackPropLearning.calculateBiasUpdates(
layer2Sensitivity, 0.1);
Assert.AreEqual(0.2522, biasUpdateVector2.getValue(0), 0.001);
Vector lastBiasUpdateVector2 = layer2.getLastBiasUpdateVector();
Assert.AreEqual(0.2522, lastBiasUpdateVector2.getValue(0), 0.001);
Vector penultimateBiasUpdateVector2 = layer2
.getPenultimateBiasUpdateVector();
Assert.AreEqual(0.0, penultimateBiasUpdateVector2.getValue(0),
0.001);
Vector biasUpdateVector1 = BackPropLearning.calculateBiasUpdates(
layer1Sensitivity, 0.1);
Assert.AreEqual(0.00495, biasUpdateVector1.getValue(0), 0.001);
Assert.AreEqual(-0.00997, biasUpdateVector1.getValue(1), 0.001);
Vector lastBiasUpdateVector1 = layer1.getLastBiasUpdateVector();
Assert.AreEqual(0.00495, lastBiasUpdateVector1.getValue(0), 0.001);
Assert.AreEqual(-0.00997, lastBiasUpdateVector1.getValue(1), 0.001);
Vector penultimateBiasUpdateVector1 = layer1
.getPenultimateBiasUpdateVector();
Assert.AreEqual(0.0, penultimateBiasUpdateVector1.getValue(0),
0.001);
Assert.AreEqual(0.0, penultimateBiasUpdateVector1.getValue(1),
0.001);
}
