/// <summary>
/// Construct a NEAT link.
/// </summary>
/// <param name="weight">The weight between the two neurons.</param>
/// <param name="fromNeuron">The source neuron.</param>
/// <param name="toNeuron">The target neuron.</param>
/// <param name="recurrent">Is this a recurrent link.</param>
public NEATLink(double weight, NEATNeuron fromNeuron,
NEATNeuron toNeuron, bool recurrent)
{
this.weight = weight;
this.fromNeuron = fromNeuron;
this.toNeuron = toNeuron;
this.recurrent = recurrent;
}
/// <summary>
/// Construct a NEAT link.
/// </summary>
/// <param name="weight">The weight between the two neurons.</param>
/// <param name="fromNeuron">The source neuron.</param>
/// <param name="toNeuron">The target neuron.</param>
/// <param name="recurrent">Is this a recurrent link.</param>
public NEATLink(double weight, NEATNeuron fromNeuron,
NEATNeuron toNeuron, bool recurrent)
{
this.weight = weight;
this.fromNeuron = fromNeuron;
this.toNeuron = toNeuron;
this.recurrent = recurrent;
}
/// <summary>
/// Convert the genes to an actual network.
/// </summary>
public override void Decode()
{
NEATPattern pattern = new NEATPattern();
IList<NEATNeuron> neurons = pattern.Neurons;
foreach (IGene gene in Neurons.Genes)
{
NEATNeuronGene neuronGene = (NEATNeuronGene)gene;
NEATNeuron neuron = new NEATNeuron(
neuronGene.NeuronType, neuronGene.Id, neuronGene
.SplitY, neuronGene.SplitX, neuronGene
.ActivationResponse);
neurons.Add(neuron);
}
// now to create the links.
foreach (IGene gene in Links.Genes)
{
NEATLinkGene linkGene = (NEATLinkGene)gene;
if (linkGene.Enabled)
{
int element = GetElementPos(linkGene.FromNeuronID);
NEATNeuron fromNeuron = neurons[element];
element = GetElementPos(linkGene.ToNeuronID);
NEATNeuron toNeuron = neurons[element];
NEATLink link = new NEATLink(linkGene.Weight,
fromNeuron, toNeuron, linkGene.IsRecurrent);
fromNeuron.OutputboundLinks.Add(link);
toNeuron.InboundLinks.Add(link);
}
}
pattern.NEATActivation = (((NEATTraining)GA).NeatActivationFunction);
pattern.ActivationFunction = (((NEATTraining)GA).OutputActivationFunction);
pattern.InputNeurons = (inputCount);
pattern.OutputNeurons = (outputCount);
pattern.Snapshot = ((NEATTraining)GA).Snapshot;
Organism = pattern.Generate();
}
/// <summary>
/// Compute the output from this synapse.
/// </summary>
/// <param name="input">The input to this synapse.</param>
/// <returns>The output from this synapse.</returns>
public INeuralData Compute(INeuralData input)
{
INeuralData result = new BasicNeuralData(ToNeuronCount);
if (this.neurons.Count == 0)
{
throw new NeuralNetworkError("This network has not been evolved yet, it has no neurons in the NEAT synapse.");
}
int flushCount = 1;
if (snapshot)
{
flushCount = networkDepth;
}
// iterate through the network FlushCount times
for (int i = 0; i < flushCount; ++i)
{
int outputIndex = 0;
int index = 0;
result.Clear();
// populate the input neurons
while (neurons[index].NeuronType == NEATNeuronType.Input)
{
neurons[index].Output = input[index];
index++;
}
// set the bias neuron
neurons[index++].Output = 1;
while (index < neurons.Count)
{
NEATNeuron currentNeuron = neurons[index];
double sum = 0;
foreach (NEATLink link in currentNeuron.InboundLinks)
{
double weight = link.Weight;
double neuronOutput = link.FromNeuron.Output;
sum += weight * neuronOutput;
}
double[] d = new double[1];
d[0] = sum / currentNeuron.ActivationResponse;
activationFunction.ActivationFunction(d, 0, 1);
neurons[index].Output = d[0];
if (currentNeuron.NeuronType == NEATNeuronType.Output)
{
result.Data[outputIndex++] = currentNeuron.Output;
}
index++;
}
}
return(result);
}
