public NeatNeuralNetwork(NeuralActivationFunction[] _neuralActivationFunctions, int _inputSize, int _outputSize, double _learnRate = -1, double _momentum = -1)
{
genome = new NeuralGenome();
neuralActivationFunctions = _neuralActivationFunctions;
genome.learnRate = _learnRate == -1 ? .1 : _learnRate;
genome.momentum = _momentum == -1 ? .4 : _momentum;
genome.InputLayer = new List <NeuralGeneNode>();
genome.HiddenLayers = new List <NeuralGeneNode>();
genome.OutputLayer = new List <NeuralGeneNode>();
genome.nodes = new List <NeuralGeneNode>();
genome.connections = new List <NeuralGeneConnection>();
genome.InitNewGenome(_inputSize, _outputSize, 0, _neuralActivationFunctions);
}
public NeatNeuralNetwork(NeuralActivationFunction[] _neuralActivationFunctions, int _inputSize, int _outputSize, int _globalInnovation, bool _firstGenome,
Func <int, float> fitnessFunction, float[] _mutationRates, Func <int, int> _increaseGlobalInnovation, double _learnRate = -1, double _momentum = -1)
{
genome = new NeuralGenome();
neuralActivationFunctions = _neuralActivationFunctions;
genome.learnRate = _learnRate == -1 ? .1 : _learnRate;
genome.momentum = _momentum == -1 ? .4 : _momentum;
genome.random = Random;
genome.InputLayer = new List <NeuralGeneNode>();
genome.HiddenLayers = new List <NeuralGeneNode>();
genome.OutputLayer = new List <NeuralGeneNode>();
genome.nodes = new List <NeuralGeneNode>();
genome.connections = new List <NeuralGeneConnection>();
genome.mutationRates = _mutationRates;
genome.fitnessFunction = fitnessFunction;
genome.InitNewGenome(_inputSize, _outputSize, _globalInnovation, _neuralActivationFunctions, _increaseGlobalInnovation, _firstGenome);
}
public NeatNeuralNetwork Crossover(NeatNeuralNetwork otherParent)
{
NeuralGenome childGenome = new NeuralGenome();
childGenome.learnRate = genome.learnRate;
childGenome.momentum = genome.momentum;
childGenome.random = Random;
childGenome.InputLayer = new List <NeuralGeneNode>();
childGenome.HiddenLayers = new List <NeuralGeneNode>();
childGenome.OutputLayer = new List <NeuralGeneNode>();
childGenome.nodes = new List <NeuralGeneNode>();
childGenome.connections = new List <NeuralGeneConnection>();
childGenome.mutationRates = genome.mutationRates;
childGenome.fitnessFunction = genome.fitnessFunction;
childGenome.InitNewGenome(genome.currInnovation, neuralActivationFunctions, genome.IncreaseGlobalInnovation, false);
// no best parent
int bestGenome = 0;
bool takeNotOptimum = false;
double randRate = Random.NextDouble();
if (randRate < 0.01f)
{
takeNotOptimum = true;
}
// find parent with best fitness
if (otherParent.genome.fitness > genome.fitness)
{
// best parent is other parent
bestGenome = 1;
}
else if (otherParent.genome.fitness < genome.fitness)
{
// best parent is thisparent
bestGenome = 2;
}
int index = 0;
if (this.genome.connections.Count > otherParent.genome.connections.Count)
{
foreach (var thisParentConnection in this.genome.connections)
{
//foreach (var otherParentConnection in otherParent.genome.connections)
//{
if (index > otherParent.genome.connections.Count - 1)
{
HandleExtraNodes(thisParentConnection, null, childGenome, bestGenome, takeNotOptimum);
}
else
{
CrossOverParents(thisParentConnection, otherParent.genome.connections[index], childGenome, bestGenome);
}
//}
index++;
}
}
else
{
foreach (var otherParentConnection in otherParent.genome.connections)
{
//foreach (var thisParentConnection in this.genome.connections)
//{
if (index > this.genome.connections.Count - 1)
{
HandleExtraNodes(null, otherParentConnection, childGenome, bestGenome, takeNotOptimum);
}
else
{
CrossOverParents(this.genome.connections[index], otherParentConnection, childGenome, bestGenome);
}
//}
index++;
}
}
NeatNeuralNetwork child = new NeatNeuralNetwork(childGenome);
return(child);
}
