public RBF(int K, int numOfEpocks, double learningRate, double maxError, List<List<double>> trainingSamples, List<List<double>> trainingLabels, List<List<double>> testSamples, List<List<double>> testLabels)
{
this.numOfEpocks = numOfEpocks;
this.trainingSamples = trainingSamples;
this.trainingLabels = trainingLabels;
this.testSamples = testSamples;
this.testLabels = testLabels;
this.maxError = maxError;
this.learningRate = learningRate;
Centroids = new List<List<double>>(); //[NumOfCluster][NumOfFeatures (means)]
Random rnd = new Random(Guid.NewGuid().GetHashCode());
int counter = K; // Num of Clusters
while (counter-- > 0)
{
int index = rnd.Next(trainingSamples.Count);
Centroids.Add(trainingSamples[index]);
}
KMean = new K_Means(ref Centroids, trainingSamples);
Variance = KMean.GetVariance;
////
////
List<int> numOfNeuronsPerLayer = new List<int>();
backpropagation = new Backpropagation();
numOfNeuronsPerLayer.Add(K);
numOfNeuronsPerLayer.Add(3);
this.neuralNetwork = new FeedforwardNeuralNetwrok(2);
this.neuralNetwork.setNetwork(numOfNeuronsPerLayer);
this.neuralNetwork.LMSsetLayer(1, new IdentityFunction());
}
/// <summary>
/// Train the network given the training samples (features) and the labels (classes),
/// then using the chosen learning algorithm to update the weights.
/// </summary>
/// <param name="trainingSamples"> Training Samples Features</param>
/// <param name="trainingLabels"> Training Labels (classes)</param>
/// <param name="learningRate">Training learning Rate</param>
/// <param name="learningAlgorithm">The learning algorithm that will be used to train the network</param>
public void train(List<List<double>> trainingSamples, List<List<double>> trainingLabels, double learningRate, LearningAlgorithm learningAlgorithm)
{
double sum = 0;
for (int i = 0; i < trainingSamples.Count; ++i)
{
List<double> output = this.feedforward(trainingSamples[i]);
this.network = learningAlgorithm.learn(learningRate, trainingSamples[i], trainingLabels[i], this.network);
for (int j = 0; j < network[0].Count; j++)
{
sum += Math.Pow(network[0][j].SignalError, 2);
}
}
ErrorSqr = sum / network[0].Count;
}
/// <summary>
/// Train the network given the training samples (features) and the labels (classes),
/// then using the chosen learning algorithm to update the weights.
/// </summary>
/// <param name="trainingSamples"> Training Samples Features</param>
/// <param name="trainingLabels"> Training Labels (classes)</param>
/// <param name="learningRate">Training learning Rate</param>
/// <param name="learningAlgorithm">The learning algorithm that will be used to train the network</param>
public void train(List <List <double> > trainingSamples, List <List <double> > trainingLabels, double learningRate, LearningAlgorithm learningAlgorithm)
{
double sum = 0;
for (int i = 0; i < trainingSamples.Count; ++i)
{
List <double> output = this.feedforward(trainingSamples[i]);
this.network = learningAlgorithm.learn(learningRate, trainingSamples[i], trainingLabels[i], this.network);
for (int j = 0; j < network[0].Count; j++)
{
sum += Math.Pow(network[0][j].SignalError, 2);
}
}
ErrorSqr = sum / network[0].Count;
}
