private void UpdateNetwork()
{
// 6.1 Update hidden layer weights
for (int i = 0; i < hidden.Neurons.Length; i++)
{
StochasticNeuron neuron = hidden.Neurons[i];
for (int j = 0; j < neuron.Weights.Length; j++)
{
neuron.Weights[j] += weightsUpdates[j][i] - learningRate * decay * neuron.Weights[j];
}
neuron.Threshold += hiddenBiasUpdates[i];
}
// 6.2 Update visible layer with reverse weights
for (int i = 0; i < visible.Neurons.Length; i++)
{
visible.Neurons[i].Threshold += visibleBiasUpdates[i];
}
visible.CopyReversedWeightsFrom(hidden);
}
/// <summary>
/// Creates a new <see cref="ActivationNetwork"/> from this instance.
/// </summary>
///
/// <param name="outputs">The number of output neurons in the last layer.</param>
/// <param name="function">The activation function to use in the last layer.</param>
///
/// <returns>An <see cref="ActivationNetwork"/> containing this network.</returns>
///
public ActivationNetwork ToActivationNetwork(IActivationFunction function, int outputs)
{
ActivationNetwork ann = new ActivationNetwork(function,
inputsCount, hidden.Neurons.Length, outputs);
// For each neuron
for (int i = 0; i < hidden.Neurons.Length; i++)
{
ActivationNeuron aneuron = ann.Layers[0].Neurons[i] as ActivationNeuron;
StochasticNeuron sneuron = hidden.Neurons[i];
// For each weight
for (int j = 0; j < sneuron.Weights.Length; j++)
{
aneuron.Weights[j] = sneuron.Weights[j];
}
aneuron.Threshold = sneuron.Threshold;
aneuron.ActivationFunction = sneuron.ActivationFunction;
}
return(ann);
}
