internal override PopulationParameters ApplyAction(PopulationParameters populationParameters)
{
populationParameters.NaturalImmunity *= 1.5;
populationParameters.NaturalImmunity = Math.Max(0.90, populationParameters.NaturalImmunity);
return(populationParameters);
}
public XorModel(PopulationParameters populationParameters, MutationParameters mutationParameters, double[][] truthTable)
{
_populationParameters = populationParameters;
_mutationParameters = mutationParameters;
_truthTable = truthTable;
_population = Enumerable.Range(0, _populationParameters.PopulationSize)
.AsParallel()
.Select(i =>
{
var genome = new NeatGenome(NetworkParameters, _mutationParameters);
genome.CreateInitialGenome();
return(new XorIndividual(genome));
})
.ToList();
}
static void XorTest()
{
Console.WriteLine("XOR challenge accepted!");
Console.WriteLine();
NetworkParameters networkParameters = new NetworkParameters(2, 1);
PopulationParameters populationParameters = new PopulationParameters(20, 10000, 5, 10);
MutationParameters mutationParameters = new MutationParameters();
double[][] XorTruthTable =
{
new double[] { 0.0f, 0.0f, 0.0f },
new double[] { 0.0f, 1.0f, 1.0f },
new double[] { 1.0f, 0.0f, 1.0f },
new double[] { 1.0f, 1.0f, 0.0f }
};
XorModel xorModel = new XorModel(populationParameters, mutationParameters, XorTruthTable);
var iteration = xorModel.Search(100, 0.00001f);
Console.WriteLine();
Console.WriteLine($"BEST. Iteration = {iteration} Error = {xorModel.BestIndividual.Error}");
var net = xorModel.BestIndividual.Genome.Network;
foreach (var xorData in XorTruthTable)
{
net.Inputs[0] = xorData[0];
net.Inputs[1] = xorData[1];
net.Activate();
Console.WriteLine($"[{xorData[0]} {xorData[1]}] = {net.Outputs[0]}");
}
Console.WriteLine();
xorModel.BestIndividual.Genome.PrintGenomeStructure();
Console.WriteLine("Dump to File");
File.WriteAllText("xor_net_genome.json", xorModel.BestIndividual.Genome.DumpToJson());
Console.WriteLine();
}
static void MnistTest()
{
Console.WriteLine("Mnist challenge accepted!");
Console.WriteLine();
var trainSet = new TrainingSet();
PopulationParameters populationParameters = new PopulationParameters(5, 100, 1, 2);
MutationParameters mutationParameters = new MutationParameters();
NetworkParameters networkParameters = new NetworkParameters(MnistDataset.ImageSize, MnistDataset.ClassCount);
MnistModel mnistModel = new MnistModel(populationParameters, mutationParameters, networkParameters, trainSet);
mnistModel.Search(2, 0.1, 100);
Console.WriteLine();
Console.WriteLine("Best individual");
Console.WriteLine(mnistModel.BestIndividual);
Console.WriteLine();
}
public SplitConnectionWeightsSearch(
PopulationParameters populationParameters,
NetworkParameters networkParameters,
ReproductionParameters reproductionParameters)
{
_populationParameters = populationParameters;
_neatPopulation = new Population(networkParameters, reproductionParameters, false);
_genomes = Range(0, _populationParameters.PopulationSize)
.Select(_ => _neatPopulation.CreateInitialGenome());
_archiveSize = _populationParameters.PopulationSize / 2;
_archive = new List <ParetoFrontPoint>(_archiveSize);
WeightSamples = Range(0, 300)
.Select(_ => RandomSource.Range(0, MaxAbsWeightValue))
.ToArray();
InputSamples = Range(0, 60)
.Select(_ => RandomSource.Range(0, 1))
.ToArray();
}
internal override PopulationParameters ApplyAction(PopulationParameters populationParameters)
{
populationParameters.ChanceOfTwoCitizensMeeting *= 0.6;
return(populationParameters);
}
internal override PopulationParameters ApplyAction(PopulationParameters populationParameters)
{
return(populationParameters);
}
internal abstract PopulationParameters ApplyAction(PopulationParameters populationParameters);
