/// <summary>
/// Gets the number of parameters in a network.
/// </summary>
private static int getNumberOfParameters(ActivationNetwork network)
{
int sum = 0;
for (int i = 0; i < network.Layers.Length; i++)
{
for (int j = 0; j < network.Layers[i].Neurons.Length; j++)
{
// number of weights plus the bias value
sum += network.Layers[i].Neurons[j].InputsCount + 1;
}
}
return(sum);
}
/// <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
{
throw new NotImplementedException("Finite difference method is not implemented");
}
}
internal static JObject SerializeToJson(ActivationNetwork network)
{
JObject result = new JObject();
result["InputsCount"] = network.inputsCount;
result["layersCount"] = network.layersCount;
// result["Outputs"] = new JArray(network.output);
JArray layers = new JArray();
for (int i = 0; i < network.layers.Length; i++)
{
ActivationLayer layer = (ActivationLayer)network.layers[i];
layers.Add(ActivationLayer.SerializeToJson(layer));
}
result["Layers"] = layers;
return(result);
}
internal static ActivationNetwork DeserializeFromJson(JObject jnetwork)
{
ActivationNetwork network = new ActivationNetwork();
network.inputsCount = jnetwork["InputsCount"].ToObject <int>();
network.layersCount = jnetwork["layersCount"].ToObject <int>();
// network.output = jnetwork["Outputs"].ToObject<double[]>();
network.layers = new Layer[network.layersCount];
int counter = 0;
foreach (JObject jlayer in jnetwork["Layers"].Children <JObject>())
{
network.layers[counter++] = ActivationLayer.DeserializeFromJson(jlayer);
}
network.SetActivationFunction(new SigmoidFunction());
return(network);
}
/// <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="useRegularization">True to use Bayesian regularization, false otherwise.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network, bool useRegularization) :
this(network, useRegularization, JacobianMethod.ByBackpropagation)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="LevenbergMarquardtLearning"/> class.
/// </summary>
///
/// <param name="network">Network to teach.</param>
///
public LevenbergMarquardtLearning(ActivationNetwork network) :
this(network, false, JacobianMethod.ByBackpropagation)
{
}
public static string Serialize(ActivationNetwork network)
{
return(SerializeToJson(network).ToString());
}
