public AdvancedNeuralNetwork(string[] inputFieldNames, string outputFieldName, int[] neuronsCount, double learningRate = 0.1, double sigmoidAlphaValue = 2, bool useRegularization = false, bool useNguyenWidrow = false, bool useSameWeights = false, JacobianMethod method = JacobianMethod.ByBackpropagation)
{
this.neuronsCount = neuronsCount;
this.learningRate = learningRate;
this.useRegularization = useRegularization;
this.useNguyenWidrow = useNguyenWidrow;
this.useSameWeights = useSameWeights;
this.method = method;
this.sigmoidAlphaValue = sigmoidAlphaValue;
this.inputFieldNames = inputFieldNames;
this.outputFieldName = outputFieldName;
// create multi-layer neural network
theNetwork = new ActivationNetwork(
new BipolarSigmoidFunction(sigmoidAlphaValue), //Andere Function möglich???
inputFieldNames.Length, neuronsCount);
if (useNguyenWidrow)
{
if (useSameWeights)
{
Accord.Math.Random.Generator.Seed = 0;
}
NguyenWidrow initializer = new NguyenWidrow(theNetwork);
initializer.Randomize();
}
// create teacher
teacher = new LevenbergMarquardtLearning(theNetwork, useRegularization, method);
// set learning rate and momentum
teacher.LearningRate = learningRate;
}
/// <summary>
/// Initializes a new instance of the <see cref="LevenbergMarquardtLearning"/> class.
/// </summary>
///
/// <param name="network">Network to teach.</param>
/// <param name="useRegularization">True to use Bayesian regularization, false otherwise.</param>
/// <param name="method">The method by which the Jacobian matrix will be calculated.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network, bool useRegularization, JacobianMethod method)
{
this.ParallelOptions = new ParallelOptions();
this.network = network;
this.numberOfParameters = getNumberOfParameters(network);
this.outputCount = network.Layers[network.Layers.Length - 1].Neurons.Length;
this.useBayesianRegularization = useRegularization;
this.method = method;
this.weights = new float[numberOfParameters];
this.hessian = new float[numberOfParameters][];
for (int i = 0; i < hessian.Length; i++)
{
hessian[i] = new float[numberOfParameters];
}
this.diagonal = new float[numberOfParameters];
this.gradient = new float[numberOfParameters];
this.jacobian = new float[numberOfParameters][];
// Will use Backpropagation method for Jacobian computation
if (method == JacobianMethod.ByBackpropagation)
{
// create weight derivatives arrays
this.weightDerivatives = new float[network.Layers.Length][][];
this.thresholdsDerivatives = new float[network.Layers.Length][];
// initialize arrays
for (int i = 0; i < network.Layers.Length; i++)
{
ActivationLayer layer = (ActivationLayer)network.Layers[i];
this.weightDerivatives[i] = new float[layer.Neurons.Length][];
this.thresholdsDerivatives[i] = new float[layer.Neurons.Length];
for (int j = 0; j < layer.Neurons.Length; j++)
{
this.weightDerivatives[i][j] = new float[layer.InputsCount];
}
}
}
else // Will use finite difference method for Jacobian computation
{
// create differential coefficient arrays
this.differentialCoefficients = createCoefficients(3);
this.derivativeStepSize = new double[numberOfParameters];
// initialize arrays
for (int i = 0; i < numberOfParameters; i++)
{
this.derivativeStepSize[i] = derivativeStep;
}
}
}
/// <summary>
/// Initializes a new instance of the <see cref="LevenbergMarquardtLearning"/> class.
/// </summary>
///
/// <param name="network">Network to teach.</param>
/// <param name="useRegularization">True to use bayesian regularization, false otherwise.</param>
/// <param name="method">The method by which the Jacobian matrix will be calculated.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network, bool useRegularization, JacobianMethod method)
{
this.network = network;
this.numberOfParameters = getNumberOfParameters(network);
this.outputCount = network.Layers[network.Layers.Length - 1].Neurons.Length;
this.useBayesianRegularization = useRegularization;
this.method = method;
this.weights = new float[numberOfParameters];
this.hessian = new float[numberOfParameters][];
for (int i = 0; i < hessian.Length; i++)
hessian[i] = new float[numberOfParameters];
this.diagonal = new float[numberOfParameters];
this.gradient = new float[numberOfParameters];
this.jacobian = new float[numberOfParameters][];
// Will use backpropagation method for Jacobian computation
if (method == JacobianMethod.ByBackpropagation)
{
// create weight derivatives arrays
this.weightDerivatives = new float[network.Layers.Length][][];
this.thresholdsDerivatives = new float[network.Layers.Length][];
// initialize arrays
for (int i = 0; i < network.Layers.Length; i++)
{
ActivationLayer layer = (ActivationLayer)network.Layers[i];
this.weightDerivatives[i] = new float[layer.Neurons.Length][];
this.thresholdsDerivatives[i] = new float[layer.Neurons.Length];
for (int j = 0; j < layer.Neurons.Length; j++)
this.weightDerivatives[i][j] = new float[layer.InputsCount];
}
}
else // Will use finite difference method for Jacobian computation
{
// create differential coefficient arrays
this.differentialCoefficients = createCoefficients(3);
this.derivativeStepSize = new double[numberOfParameters];
// initialize arrays
for (int i = 0; i < numberOfParameters; i++)
this.derivativeStepSize[i] = derivativeStep;
}
}
/// <summary>
/// Initializes a new instance of the <see cref="LevenbergMarquardtLearning"/> class.
/// </summary>
///
/// <param name="network">Network to teach.</param>
/// <param name="method">The method by which the Jacobian matrix will be calculated.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network, JacobianMethod method)
: this(network, false, method)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="LevenbergMarquardtLearning"/> class.
/// </summary>
///
/// <param name="network">Network to teach.</param>
/// <param name="method">The method by which the Jacobian matrix will be calculated.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network, JacobianMethod method)
: this(network, false, method)
{
}
