public NeuralNetwork(NeuralNetworkParameters parameters, IContinuousDistribution rng)
{
NetworkParameters = parameters;
HiddenWeights = CreateMatrix.Random <float>(NetworkParameters.HiddenLayerNeuronCount, NetworkParameters.InputCount, rng);
HiddenBiases = CreateVector.Random <float>(NetworkParameters.HiddenLayerNeuronCount, rng);
OutputWeights = CreateMatrix.Random <float>(NetworkParameters.OutputCount, NetworkParameters.HiddenLayerNeuronCount, rng);
OutputBiases = CreateVector.Random <float>(NetworkParameters.OutputCount, rng);
}
public void Reset()
{
mBias = CreateVector.Random <double>(mBias.Count, new Normal(0.0, 1.0));
if (mWeights != null)
{
mWeights = CreateMatrix.Random <double>(mWeights.RowCount, mWeights.ColumnCount, new Normal(0.0, 1.0 / Math.Sqrt(mWeights.ColumnCount)));
}
}
public SimplePerceptron(int N, double learningRate, Func <double, double> activationFunction, Func <double, double> activationFunctionDerivative, bool adaptiveLearningRate)
{
this.N = N;
this.W = CreateVector.Random <double>(N + 1, new ContinuousUniform(-1d, 1d));
this.ActivationFunction = activationFunction;
this.ActivationFunctionDerivative = activationFunctionDerivative;
this.LearningRate = learningRate;
this.AdaptiveLearningRate = adaptiveLearningRate;
}
public OjaNetwork(double learningRate, int epochs, List <Vector <double> > values)
{
this.epochs = epochs;
var columns = CreateMatrix.DenseOfRowVectors(values).EnumerateColumns();
var mean = CreateVector.DenseOfEnumerable(columns.Select(Statistics.Mean));
var std = CreateVector.DenseOfEnumerable(columns.Select(Statistics.StandardDeviation));
this.values = values.Select(v => (v - mean) / std).ToList();
this.variables = values[1].Count;
this.W = CreateVector.Random <double>(variables, new ContinuousUniform(-1, 1));
this.LearningRate = learningRate;
}
public KohonenNetwork(List <Vector <double> > values, int n, bool weightEntries)
{
this.values = Normalize(values);
W = new Vector <double> [n, n];
N = n;
inputLength = this.values[0].Count;
var indexes = MathNet.Numerics.Combinatorics.GenerateVariationWithRepetition(this.values.Count, n * n);
var current = 0;
for (int i = 0; i < n; i++)
{
for (int j = 0; j < n; j++)
{
W[i, j] = !weightEntries?CreateVector.Random <double>(inputLength, new ContinuousUniform(0, 1)) : this.values[indexes[current++]];
}
}
}
public void Learn(
Vector <double>[] trainingInput,
Vector <double>[] trainingOutput,
Vector <double>[] testInput,
Vector <double>[] testOutput,
int batch,
double minError,
int epochs)
{
Contract.Requires(trainingInput.Length == trainingOutput.Length);
Contract.Requires(testInput.Length == testOutput.Length);
Contract.Requires(trainingInput[0].Count == N + 1);
Contract.Requires(testInput[0].Count == N + 1);
double[] desiredTrainingOutput = trainingOutput.Select(o => o.At(0)).ToArray();
double[] desiredTestOutput = trainingOutput.Select(o => o.At(0)).ToArray();
//Agrego el valor 1 al principio del input.
Vector <double>[] input = new Vector <double> [trainingInput.Length];
for (int i = 0; i < input.Length; i++)
{
input[i] = Vector <double> .Build.DenseOfEnumerable(new double[] { 1 }.Concat(trainingInput[i]));
}
int p = input.Length;
Vector <double> w = CreateVector.Random <double>(N + 1, new ContinuousUniform(-1d, 1d));
Vector <double> deltaW = null;
double error = 1, error_min = p * 2;
Vector <double> w_min = w;
for (int i = 0, n = 0; i < epochs && error_min > minError; i++, n++)
{
if (n > 100 * p)
{
w = CreateVector.Random <double>(N + 1, new ContinuousUniform(-1d, 1d));
n = 0;
}
int[] rand = Combinatorics.GeneratePermutation(input.Length);
double lr = this.AdaptiveLearningRate ? optimizing(w, input, desiredTrainingOutput, batch, rand) : LearningRate;
int j;
for (j = 0; j < input.Length; j++)
{
int ix = rand[j];
double h = input[ix] * w;
double act = ActivationFunction(h);
Vector <double> delta = lr * (desiredTrainingOutput[ix] - act) * input[ix] * ActivationFunctionDerivative(h);
deltaW = deltaW == null ? delta : deltaW + delta;
if (j % batch == 0)
{
w += deltaW;
deltaW = null;
error = CalculateError(input, desiredTrainingOutput, w);
if (error < error_min)
{
error_min = error;
w_min = w;
}
}
}
if (j % batch != 0)
{
w += deltaW;
deltaW = null;
error = CalculateError(input, desiredTrainingOutput, w);
if (error < error_min)
{
error_min = error;
w_min = w;
}
}
}
W = w_min;
}
public Layer(int size, int sizeofPreviousLayer) : this(CreateVector.Random <double>(size, new Normal(0.0, 1.0)),
sizeofPreviousLayer > 0 ? CreateMatrix.Random <double>(size, sizeofPreviousLayer, new Normal(0.0, 1.0 / Math.Sqrt(sizeofPreviousLayer))) : null)
{
}
