/// <inheritdoc/>
public NEATGenome Factor(EncogRandom rnd, NEATPopulation pop,
int inputCount, int outputCount,
double connectionDensity)
{
return new NEATGenome(rnd, pop, inputCount, outputCount,
connectionDensity);
}
public DisplayBoxes(NEATPopulation thePopulation)
{
InitializeComponent();
testCase.InitTestCase(0);
this.pop = thePopulation;
Render();
}
/// <inheritdoc/>
public NEATGenome Factor(EncogRandom rnd, NEATPopulation pop,
int inputCount, int outputCount,
double connectionDensity)
{
return(new NEATGenome(rnd, pop, inputCount, outputCount,
connectionDensity));
}
/// <summary>
/// Create a NEAT population.
/// </summary>
/// <param name="architecture">The architecture string to use.</param>
/// <param name="input">The input count.</param>
/// <param name="output">The output count.</param>
/// <returns>The population.</returns>
public IMLMethod Create(String architecture, int input,
int output)
{
if (input <= 0)
{
throw new EncogError("Must have at least one input for NEAT.");
}
if (output <= 0)
{
throw new EncogError("Must have at least one output for NEAT.");
}
IDictionary<String, String> args = ArchitectureParse.ParseParams(architecture);
ParamsHolder holder = new ParamsHolder(args);
int populationSize = holder.GetInt(
MLMethodFactory.PropertyPopulationSize, false, 1000);
int cycles = holder.GetInt(
MLMethodFactory.PropertyCycles, false, NEATPopulation.DefaultCycles);
IActivationFunction af = this.factory.Create(
holder.GetString(MLMethodFactory.PropertyAF, false, MLActivationFactory.AF_SSIGMOID));
NEATPopulation pop = new NEATPopulation(input, output, populationSize);
pop.Reset();
pop.ActivationCycles = cycles;
pop.NEATActivationFunction = af;
return pop;
}
/// <summary>
/// Construct a NEAT or HyperNEAT trainer.
/// </summary>
/// <param name="calculateScore">The score function.</param>
/// <param name="inputCount">The input count.</param>
/// <param name="outputCount">The output count.</param>
/// <param name="populationSize">The population size.</param>
/// <returns></returns>
public static TrainEA ConstructNEATTrainer(
ICalculateScore calculateScore, int inputCount,
int outputCount, int populationSize)
{
var pop = new NEATPopulation(inputCount, outputCount,
populationSize);
pop.Reset();
return ConstructNEATTrainer(pop, calculateScore);
}
/// <summary>
/// Construct a NEAT or HyperNEAT trainer.
/// </summary>
/// <param name="calculateScore">The score function.</param>
/// <param name="inputCount">The input count.</param>
/// <param name="outputCount">The output count.</param>
/// <param name="populationSize">The population size.</param>
/// <returns></returns>
public static TrainEA ConstructNEATTrainer(
ICalculateScore calculateScore, int inputCount,
int outputCount, int populationSize)
{
var pop = new NEATPopulation(inputCount, outputCount,
populationSize);
pop.Reset();
return(ConstructNEATTrainer(pop, calculateScore));
}
public void ResetTraining()
{
Substrate substrate = SubstrateFactory.factorSandwichSubstrate(11, 11);
BoxesScore score = new BoxesScore(11);
pop = new NEATPopulation(substrate, 500);
pop.ActivationCycles = 4;
pop.Reset();
train = NEATUtil.ConstructNEATTrainer(pop, score);
OriginalNEATSpeciation speciation = new OriginalNEATSpeciation();
train.Speciation = new OriginalNEATSpeciation();
}
private void Validate(NEATPopulation pop)
{
Assert.AreEqual(0.3, pop.OldAgePenalty);
Assert.AreEqual(50, pop.OldAgeThreshold);
Assert.AreEqual(10, pop.PopulationSize);
Assert.AreEqual(0.2, pop.SurvivalRate);
Assert.AreEqual(10, pop.YoungBonusAgeThreshold);
Assert.AreEqual(0.3, pop.YoungScoreBonus);
// see if the population can actually be used to train
IMLDataSet trainingSet = new BasicMLDataSet(XOR.XORInput, XOR.XORIdeal);
ICalculateScore score = new TrainingSetScore(trainingSet);
NEATTraining train = new NEATTraining(score, pop);
train.Iteration();
}
/// <summary>
/// Program entry point.
/// </summary>
/// <param name="app">Holds arguments and other info.</param>
public void Execute(IExampleInterface app)
{
IMLDataSet trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
NEATPopulation pop = new NEATPopulation(2, 1, 1000);
pop.Reset();
pop.InitialConnectionDensity = 1.0; // not required, but speeds processing.
ICalculateScore score = new TrainingSetScore(trainingSet);
// train the neural network
TrainEA train = NEATUtil.ConstructNEATTrainer(pop,score);
EncogUtility.TrainToError(train, 0.01);
NEATNetwork network = (NEATNetwork)train.CODEC.Decode(train.BestGenome);
// test the neural network
Console.WriteLine(@"Neural Network Results:");
EncogUtility.Evaluate(network, trainingSet);
}
/// <summary>
/// Program entry point.
/// </summary>
/// <param name="app">Holds arguments and other info.</param>
public void Execute(IExampleInterface app)
{
IMLDataSet trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
var pop = new NEATPopulation(2, 1, 1000);
ICalculateScore score = new TrainingSetScore(trainingSet);
// train the neural network
var step = new ActivationStep();
step.Center = 0.5;
pop.OutputActivationFunction = step;
var train = new NEATTraining(score, pop);
EncogUtility.TrainToError(train, 0.01);
var network = (NEATNetwork) train.Method;
network.ClearContext();
// test the neural network
Console.WriteLine(@"Neural Network Results:");
EncogUtility.Evaluate(network, trainingSet);
}
/// <inheritdoc/>
public Object Read(Stream istream)
{
long nextInnovationId = 0;
long nextGeneId = 0;
var result = new NEATPopulation();
var innovationList = new NEATInnovationList {Population = result};
result.Innovations = innovationList;
var reader = new EncogReadHelper(istream);
EncogFileSection section;
while ((section = reader.ReadNextSection()) != null)
{
if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("INNOVATIONS"))
{
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection
.SplitColumns(line);
var innovation = new NEATInnovation();
var innovationId = int.Parse(cols[1]);
innovation.InnovationId = innovationId;
innovation.NeuronId = int.Parse(cols[2]);
result.Innovations.Innovations[cols[0]] = innovation;
nextInnovationId = Math.Max(nextInnovationId, innovationId + 1);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("SPECIES"))
{
NEATGenome lastGenome = null;
BasicSpecies lastSpecies = null;
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
if (String.Compare(cols[0], "s", StringComparison.OrdinalIgnoreCase) == 0)
{
lastSpecies = new BasicSpecies
{
Population = result,
Age = int.Parse(cols[1]),
BestScore = CSVFormat.EgFormat.Parse(cols[2]),
GensNoImprovement = int.Parse(cols[3])
};
result.Species.Add(lastSpecies);
}
else if (String.Compare(cols[0], "g", StringComparison.OrdinalIgnoreCase) == 0)
{
bool isLeader = lastGenome == null;
lastGenome = new NEATGenome
{
InputCount = result.InputCount,
OutputCount = result.OutputCount,
Species = lastSpecies,
AdjustedScore = CSVFormat.EgFormat.Parse(cols[1]),
Score = CSVFormat.EgFormat.Parse(cols[2]),
BirthGeneration = int.Parse(cols[3])
};
lastSpecies.Add(lastGenome);
if (isLeader)
{
lastSpecies.Leader = lastGenome;
}
}
else if (String.Compare(cols[0], "n", StringComparison.OrdinalIgnoreCase) == 0)
{
var neuronGene = new NEATNeuronGene();
int geneId = int.Parse(cols[1]);
neuronGene.Id = geneId;
IActivationFunction af = EncogFileSection.ParseActivationFunction(cols[2]);
neuronGene.ActivationFunction = af;
neuronGene.NeuronType = PersistNEATPopulation.StringToNeuronType(cols[3]);
neuronGene.InnovationId = int.Parse(cols[4]);
lastGenome.NeuronsChromosome.Add(neuronGene);
nextGeneId = Math.Max(geneId + 1, nextGeneId);
}
else if (String.Compare(cols[0], "l", StringComparison.OrdinalIgnoreCase) == 0)
{
var linkGene = new NEATLinkGene
{
Id = int.Parse(cols[1]),
Enabled = (int.Parse(cols[2]) > 0),
FromNeuronId = int.Parse(cols[3]),
ToNeuronId = int.Parse(cols[4]),
Weight = CSVFormat.EgFormat.Parse(cols[5]),
InnovationId = int.Parse(cols[6])
};
lastGenome.LinksChromosome.Add(linkGene);
}
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("CONFIG"))
{
IDictionary<string, string> prm = section.ParseParams();
string afStr = prm[NEATPopulation.PropertyNEATActivation];
if (String.Compare(afStr, TypeCppn, StringComparison.OrdinalIgnoreCase) == 0)
{
HyperNEATGenome.BuildCPPNActivationFunctions(result.ActivationFunctions);
}
else
{
result.NEATActivationFunction = EncogFileSection.ParseActivationFunction(prm,
NEATPopulation.PropertyNEATActivation);
}
result.ActivationCycles = EncogFileSection.ParseInt(prm,
PersistConst.ActivationCycles);
result.InputCount = EncogFileSection.ParseInt(prm,
PersistConst.InputCount);
result.OutputCount = EncogFileSection.ParseInt(prm,
PersistConst.OutputCount);
result.PopulationSize = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyPopulationSize);
result.SurvivalRate = EncogFileSection.ParseDouble(prm,
NEATPopulation.PropertySurvivalRate);
result.ActivationCycles = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyCycles);
}
}
// set factories
if (result.IsHyperNEAT)
{
result.GenomeFactory = new FactorHyperNEATGenome();
result.CODEC = new HyperNEATCODEC();
}
else
{
result.GenomeFactory = new FactorNEATGenome();
result.CODEC = new NEATCODEC();
}
// set the next ID's
result.InnovationIDGenerate.CurrentID = nextInnovationId;
result.GeneIdGenerate.CurrentID = nextGeneId;
// find first genome, which should be the best genome
if (result.Species.Count > 0)
{
ISpecies species = result.Species[0];
if (species.Members.Count > 0)
{
result.BestGenome = species.Members[0];
}
}
return result;
}
/// <summary>
/// Read the object.
/// </summary>
/// <param name="mask0">The stream to read the object from.</param>
/// <returns>The object that was loaded.</returns>
public virtual Object Read(Stream mask0)
{
var result = new NEATPopulation();
var innovationList = new NEATInnovationList {Population = result};
result.Innovations = innovationList;
var ins0 = new EncogReadHelper(mask0);
IDictionary<Int32, ISpecies> speciesMap = new Dictionary<Int32, ISpecies>();
IDictionary<ISpecies, Int32> leaderMap = new Dictionary<ISpecies, Int32>();
IDictionary<Int32, IGenome> genomeMap = new Dictionary<Int32, IGenome>();
EncogFileSection section;
while ((section = ins0.ReadNextSection()) != null)
{
if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("INNOVATIONS"))
{
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
var innovation = new NEATInnovation
{
InnovationID = Int32.Parse(cols[0]),
InnovationType = StringToInnovationType(cols[1]),
NeuronType = StringToNeuronType(cols[2]),
SplitX = CSVFormat.EgFormat.Parse(cols[3]),
SplitY = CSVFormat.EgFormat.Parse(cols[4]),
NeuronID = Int32.Parse(cols[5]),
FromNeuronID = Int32.Parse(cols[6]),
ToNeuronID = Int32.Parse(cols[7])
};
result.Innovations.Add(innovation);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("SPECIES"))
{
foreach (String line in section.Lines)
{
String[] cols = line.Split(',');
var species = new BasicSpecies
{
SpeciesID = Int32.Parse(cols[0]),
Age = Int32.Parse(cols[1]),
BestScore = CSVFormat.EgFormat.Parse(cols[2]),
GensNoImprovement = Int32.Parse(cols[3]),
SpawnsRequired = CSVFormat.EgFormat
.Parse(cols[4])
};
species.SpawnsRequired = CSVFormat.EgFormat
.Parse(cols[5]);
leaderMap[(species)] = (Int32.Parse(cols[6]));
result.Species.Add(species);
speciesMap[((int) species.SpeciesID)] = (species);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("GENOMES"))
{
NEATGenome lastGenome = null;
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
if (cols[0].Equals("g", StringComparison.InvariantCultureIgnoreCase))
{
lastGenome = new NEATGenome
{
NeuronsChromosome = new Chromosome(),
LinksChromosome = new Chromosome()
};
lastGenome.Chromosomes.Add(lastGenome.NeuronsChromosome);
lastGenome.Chromosomes.Add(lastGenome.LinksChromosome);
lastGenome.GenomeID = Int32.Parse(cols[1]);
lastGenome.SpeciesID = Int32.Parse(cols[2]);
lastGenome.AdjustedScore = CSVFormat.EgFormat
.Parse(cols[3]);
lastGenome.AmountToSpawn = CSVFormat.EgFormat
.Parse(cols[4]);
lastGenome.NetworkDepth = Int32.Parse(cols[5]);
lastGenome.Score = CSVFormat.EgFormat.Parse(cols[6]);
result.Add(lastGenome);
genomeMap[(int) lastGenome.GenomeID] = lastGenome;
}
else if (cols[0].Equals("n", StringComparison.InvariantCultureIgnoreCase))
{
var neuronGene = new NEATNeuronGene
{
Id = Int32.Parse(cols[1]),
NeuronType = StringToNeuronType(cols[2]),
Enabled = Int32.Parse(cols[3]) > 0,
InnovationId = Int32.Parse(cols[4]),
ActivationResponse = CSVFormat.EgFormat
.Parse(cols[5]),
SplitX = CSVFormat.EgFormat.Parse(cols[6]),
SplitY = CSVFormat.EgFormat.Parse(cols[7])
};
lastGenome.Neurons.Add(neuronGene);
}
else if (cols[0].Equals("l", StringComparison.InvariantCultureIgnoreCase))
{
var linkGene = new NEATLinkGene();
linkGene.Id = Int32.Parse(cols[1]);
linkGene.Enabled = Int32.Parse(cols[2]) > 0;
linkGene.Recurrent = Int32.Parse(cols[3]) > 0;
linkGene.FromNeuronID = Int32.Parse(cols[4]);
linkGene.ToNeuronID = Int32.Parse(cols[5]);
linkGene.Weight = CSVFormat.EgFormat.Parse(cols[6]);
linkGene.InnovationId = Int32.Parse(cols[7]);
lastGenome.Links.Add(linkGene);
}
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("CONFIG"))
{
IDictionary<String, String> paras = section.ParseParams();
result.NeatActivationFunction = EncogFileSection
.ParseActivationFunction(paras,
NEATPopulation.PropertyNEATActivation);
result.OutputActivationFunction = EncogFileSection
.ParseActivationFunction(paras,
NEATPopulation.PropertyOutputActivation);
result.Snapshot = EncogFileSection.ParseBoolean(paras,
PersistConst.Snapshot);
result.InputCount = EncogFileSection.ParseInt(paras,
PersistConst.InputCount);
result.OutputCount = EncogFileSection.ParseInt(paras,
PersistConst.OutputCount);
result.OldAgePenalty = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertyOldAgePenalty);
result.OldAgeThreshold = EncogFileSection.ParseInt(paras,
PopulationConst.PropertyOldAgeThreshold);
result.PopulationSize = EncogFileSection.ParseInt(paras,
PopulationConst.PropertyPopulationSize);
result.SurvivalRate = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertySurvivalRate);
result.YoungBonusAgeThreshhold = EncogFileSection.ParseInt(
paras, PopulationConst.PropertyYoungAgeThreshold);
result.YoungScoreBonus = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertyYoungAgeBonus);
result.GenomeIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextGenomeID);
result.InnovationIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextInnovationID);
result.GeneIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextGeneID);
result.SpeciesIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextSpeciesID);
}
}
// now link everything up
// first put all the genomes into correct species
foreach (IGenome genome in result.Genomes)
{
var neatGenome = (NEATGenome) genome;
var speciesId = (int) neatGenome.SpeciesID;
if( speciesMap.ContainsKey(speciesId))
{
ISpecies s = speciesMap[speciesId];
s.Members.Add(neatGenome);
}
neatGenome.InputCount = result.InputCount;
neatGenome.OutputCount = result.OutputCount;
}
// set the species leader links
foreach (ISpecies species in leaderMap.Keys)
{
int leaderID = leaderMap[species];
IGenome leader = genomeMap[leaderID];
species.Leader = leader;
((BasicSpecies) species).Population = result;
}
return result;
}
/// <summary>
/// Construct a NEAT (or HyperNEAT trainer.
/// </summary>
/// <param name="population">The population.</param>
/// <param name="calculateScore">The score function.</param>
/// <returns>The NEAT EA trainer.</returns>
public static TrainEA ConstructNEATTrainer(NEATPopulation population,
ICalculateScore calculateScore)
{
var result = new TrainEA(population, calculateScore)
{
Speciation = new OriginalNEATSpeciation()
};
result.Selection = new TruncationSelection(result, 0.3);
var weightMutation = new CompoundOperator();
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(1),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(2),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(3),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectProportion(0.02),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(1),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(2),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(3),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectProportion(0.02),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(1),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(2),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(3),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.01,
new NEATMutateWeights(new SelectProportion(0.02),
new MutateResetLinkWeight()));
weightMutation.Components.FinalizeStructure();
result.ChampMutation = weightMutation;
result.AddOperation(0.5, new NEATCrossover());
result.AddOperation(0.494, weightMutation);
result.AddOperation(0.0005, new NEATMutateAddNode());
result.AddOperation(0.005, new NEATMutateAddLink());
result.AddOperation(0.0005, new NEATMutateRemoveLink());
result.Operators.FinalizeStructure();
if (population.IsHyperNEAT)
{
result.CODEC = new HyperNEATCODEC();
}
else
{
result.CODEC = new NEATCODEC();
}
return(result);
}
/// <summary>
/// Construct a NEAT (or HyperNEAT trainer.
/// </summary>
/// <param name="population">The population.</param>
/// <param name="calculateScore">The score function.</param>
/// <returns>The NEAT EA trainer.</returns>
public static TrainEA ConstructNEATTrainer(NEATPopulation population,
ICalculateScore calculateScore)
{
var result = new TrainEA(population, calculateScore) {Speciation = new OriginalNEATSpeciation()};
result.Selection = new TruncationSelection(result, 0.3);
var weightMutation = new CompoundOperator();
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(1),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(2),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(3),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectProportion(0.02),
new MutatePerturbLinkWeight(0.02)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(1),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(2),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectFixed(3),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.1125,
new NEATMutateWeights(new SelectProportion(0.02),
new MutatePerturbLinkWeight(1)));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(1),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(2),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.03,
new NEATMutateWeights(new SelectFixed(3),
new MutateResetLinkWeight()));
weightMutation.Components.Add(
0.01,
new NEATMutateWeights(new SelectProportion(0.02),
new MutateResetLinkWeight()));
weightMutation.Components.FinalizeStructure();
result.ChampMutation = weightMutation;
result.AddOperation(0.5, new NEATCrossover());
result.AddOperation(0.494, weightMutation);
result.AddOperation(0.0005, new NEATMutateAddNode());
result.AddOperation(0.005, new NEATMutateAddLink());
result.AddOperation(0.0005, new NEATMutateRemoveLink());
result.Operators.FinalizeStructure();
if (population.IsHyperNEAT)
{
result.CODEC = new HyperNEATCODEC();
}
else
{
result.CODEC = new NEATCODEC();
}
return result;
}
/// <inheritdoc/>
public Object Read(Stream istream)
{
long nextInnovationId = 0;
long nextGeneId = 0;
var result = new NEATPopulation();
var innovationList = new NEATInnovationList {
Population = result
};
result.Innovations = innovationList;
var reader = new EncogReadHelper(istream);
EncogFileSection section;
while ((section = reader.ReadNextSection()) != null)
{
if (section.SectionName.Equals("NEAT-POPULATION") &&
section.SubSectionName.Equals("INNOVATIONS"))
{
foreach (String line in section.Lines)
{
IList <String> cols = EncogFileSection
.SplitColumns(line);
var innovation = new NEATInnovation();
var innovationId = int.Parse(cols[1]);
innovation.InnovationId = innovationId;
innovation.NeuronId = int.Parse(cols[2]);
result.Innovations.Innovations[cols[0]] = innovation;
nextInnovationId = Math.Max(nextInnovationId, innovationId + 1);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION") &&
section.SubSectionName.Equals("SPECIES"))
{
NEATGenome lastGenome = null;
BasicSpecies lastSpecies = null;
foreach (String line in section.Lines)
{
IList <String> cols = EncogFileSection.SplitColumns(line);
if (String.Compare(cols[0], "s", StringComparison.OrdinalIgnoreCase) == 0)
{
lastSpecies = new BasicSpecies
{
Population = result,
Age = int.Parse(cols[1]),
BestScore = CSVFormat.EgFormat.Parse(cols[2]),
GensNoImprovement = int.Parse(cols[3])
};
result.Species.Add(lastSpecies);
}
else if (String.Compare(cols[0], "g", StringComparison.OrdinalIgnoreCase) == 0)
{
bool isLeader = lastGenome == null;
lastGenome = new NEATGenome
{
InputCount = result.InputCount,
OutputCount = result.OutputCount,
Species = lastSpecies,
AdjustedScore = CSVFormat.EgFormat.Parse(cols[1]),
Score = CSVFormat.EgFormat.Parse(cols[2]),
BirthGeneration = int.Parse(cols[3])
};
lastSpecies.Add(lastGenome);
if (isLeader)
{
lastSpecies.Leader = lastGenome;
}
}
else if (String.Compare(cols[0], "n", StringComparison.OrdinalIgnoreCase) == 0)
{
var neuronGene = new NEATNeuronGene();
int geneId = int.Parse(cols[1]);
neuronGene.Id = geneId;
IActivationFunction af = EncogFileSection.ParseActivationFunction(cols[2]);
neuronGene.ActivationFunction = af;
neuronGene.NeuronType = PersistNEATPopulation.StringToNeuronType(cols[3]);
neuronGene.InnovationId = int.Parse(cols[4]);
lastGenome.NeuronsChromosome.Add(neuronGene);
nextGeneId = Math.Max(geneId + 1, nextGeneId);
}
else if (String.Compare(cols[0], "l", StringComparison.OrdinalIgnoreCase) == 0)
{
var linkGene = new NEATLinkGene
{
Id = int.Parse(cols[1]),
Enabled = (int.Parse(cols[2]) > 0),
FromNeuronId = int.Parse(cols[3]),
ToNeuronId = int.Parse(cols[4]),
Weight = CSVFormat.EgFormat.Parse(cols[5]),
InnovationId = int.Parse(cols[6])
};
lastGenome.LinksChromosome.Add(linkGene);
}
}
}
else if (section.SectionName.Equals("NEAT-POPULATION") &&
section.SubSectionName.Equals("CONFIG"))
{
IDictionary <string, string> prm = section.ParseParams();
string afStr = prm[NEATPopulation.PropertyNEATActivation];
if (String.Compare(afStr, TypeCppn, StringComparison.OrdinalIgnoreCase) == 0)
{
HyperNEATGenome.BuildCPPNActivationFunctions(result.ActivationFunctions);
}
else
{
result.NEATActivationFunction = EncogFileSection.ParseActivationFunction(prm,
NEATPopulation.PropertyNEATActivation);
}
result.ActivationCycles = EncogFileSection.ParseInt(prm,
PersistConst.ActivationCycles);
result.InputCount = EncogFileSection.ParseInt(prm,
PersistConst.InputCount);
result.OutputCount = EncogFileSection.ParseInt(prm,
PersistConst.OutputCount);
result.PopulationSize = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyPopulationSize);
result.SurvivalRate = EncogFileSection.ParseDouble(prm,
NEATPopulation.PropertySurvivalRate);
result.ActivationCycles = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyCycles);
}
}
// set factories
if (result.IsHyperNEAT)
{
result.GenomeFactory = new FactorHyperNEATGenome();
result.CODEC = new HyperNEATCODEC();
}
else
{
result.GenomeFactory = new FactorNEATGenome();
result.CODEC = new NEATCODEC();
}
// set the next ID's
result.InnovationIDGenerate.CurrentID = nextInnovationId;
result.GeneIdGenerate.CurrentID = nextGeneId;
// find first genome, which should be the best genome
if (result.Species.Count > 0)
{
ISpecies species = result.Species[0];
if (species.Members.Count > 0)
{
result.BestGenome = species.Members[0];
}
}
return(result);
}
/// <summary>
/// Builds and trains a neat network.
/// </summary>
/// <param name="aset">The IMLDataset.</param>
/// <param name="inputcounts">The inputcounts.</param>
/// <param name="outputcounts">The outputcounts.</param>
/// <param name="populationsize">The populationsize.</param>
/// <param name="ToErrorTraining">To error rate you want to train too.</param>
/// <returns>a trained netnetwork.</returns>
public static NEATNetwork BuildTrainNeatNetwork(IMLDataSet aset, int inputcounts, int outputcounts, int populationsize, double ToErrorTraining)
{
NEATPopulation pop = new NEATPopulation(inputcounts, outputcounts, populationsize);
ICalculateScore score = new TrainingSetScore(aset);
// train the neural network
ActivationStep step = new ActivationStep();
step.Center = 0.5;
pop.OutputActivationFunction = step;
NEATTraining train = new NEATTraining(score, pop);
EncogUtility.TrainToError(train, ToErrorTraining);
NEATNetwork network = (NEATNetwork)train.Method;
return network;
}
public virtual object Read(Stream mask0)
{
IDictionary<ISpecies, int> dictionary2;
IDictionary<int, IGenome> dictionary3;
EncogFileSection section;
IDictionary<string, string> dictionary4;
int num;
int num2;
NEATPopulation population = new NEATPopulation();
NEATInnovationList list = new NEATInnovationList {
Population = population
};
population.Innovations = list;
EncogReadHelper helper = new EncogReadHelper(mask0);
IDictionary<int, ISpecies> dictionary = new Dictionary<int, ISpecies>();
goto Label_0BD6;
Label_0023:
if ((section = helper.ReadNextSection()) != null)
{
if (!section.SectionName.Equals("NEAT-POPULATION"))
{
goto Label_085C;
}
if (section.SubSectionName.Equals("INNOVATIONS"))
{
using (IEnumerator<string> enumerator = section.Lines.GetEnumerator())
{
string str;
IList<string> list2;
NEATInnovation innovation;
NEATInnovation innovation2;
goto Label_0A6C;
Label_0A43:
innovation = innovation2;
if ((((uint) num2) - ((uint) num)) <= uint.MaxValue)
{
}
population.Innovations.Add(innovation);
Label_0A6C:
if (enumerator.MoveNext())
{
goto Label_0B54;
}
goto Label_0AD7;
Label_0A7A:
innovation2.SplitY = CSVFormat.EgFormat.Parse(list2[4]);
innovation2.NeuronID = int.Parse(list2[5]);
innovation2.FromNeuronID = int.Parse(list2[6]);
innovation2.ToNeuronID = int.Parse(list2[7]);
goto Label_0A43;
Label_0AD7:
if ((((uint) num2) - ((uint) num)) >= 0)
{
goto Label_0023;
}
Label_0AEF:
innovation2 = new NEATInnovation();
innovation2.InnovationID = int.Parse(list2[0]);
innovation2.InnovationType = StringToInnovationType(list2[1]);
innovation2.NeuronType = StringToNeuronType(list2[2]);
innovation2.SplitX = CSVFormat.EgFormat.Parse(list2[3]);
if (0 == 0)
{
goto Label_0A7A;
}
goto Label_0023;
Label_0B54:
str = enumerator.Current;
do
{
list2 = EncogFileSection.SplitColumns(str);
}
while (0 != 0);
goto Label_0AEF;
}
}
if (((uint) num) <= uint.MaxValue)
{
goto Label_085C;
}
goto Label_030B;
}
using (IEnumerator<IGenome> enumerator4 = population.Genomes.GetEnumerator())
{
IGenome genome3;
NEATGenome genome4;
ISpecies species3;
Label_0040:
if (enumerator4.MoveNext())
{
goto Label_00D6;
}
goto Label_0102;
Label_0051:
genome4.OutputCount = population.OutputCount;
if ((((uint) num) - ((uint) num2)) >= 0)
{
goto Label_0040;
}
Label_007D:
if (dictionary.ContainsKey(num))
{
goto Label_00BA;
}
Label_0087:
genome4.InputCount = population.InputCount;
goto Label_0051;
Label_0096:
num = (int) genome4.SpeciesID;
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
}
goto Label_007D;
Label_00BA:
species3 = dictionary[num];
species3.Members.Add(genome4);
goto Label_0087;
Label_00D6:
genome3 = enumerator4.Current;
genome4 = (NEATGenome) genome3;
goto Label_0096;
}
Label_0102:
using (IEnumerator<ISpecies> enumerator5 = dictionary2.Keys.GetEnumerator())
{
ISpecies current;
goto Label_011F;
Label_0112:
((BasicSpecies) current).Population = population;
Label_011F:
if (enumerator5.MoveNext())
{
current = enumerator5.Current;
num2 = dictionary2[current];
do
{
IGenome genome5 = dictionary3[num2];
current.Leader = genome5;
}
while (-1 == 0);
goto Label_0112;
}
return population;
}
Label_016E:
population.YoungScoreBonus = EncogFileSection.ParseDouble(dictionary4, "youngAgeBonus");
population.GenomeIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextGenomeID");
population.InnovationIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextInnovationID");
population.GeneIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextGeneID");
population.SpeciesIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextSpeciesID");
goto Label_0023;
Label_0201:
population.SurvivalRate = EncogFileSection.ParseDouble(dictionary4, "survivalRate");
if (0 != 0)
{
goto Label_03AA;
}
goto Label_02E9;
Label_0242:
population.OldAgePenalty = EncogFileSection.ParseDouble(dictionary4, "oldAgePenalty");
population.OldAgeThreshold = EncogFileSection.ParseInt(dictionary4, "oldAgeThreshold");
Label_0266:
population.PopulationSize = EncogFileSection.ParseInt(dictionary4, "populationSize");
if (((uint) num2) <= uint.MaxValue)
{
if ((((uint) num2) - ((uint) num2)) >= 0)
{
if ((((uint) num) + ((uint) num2)) > uint.MaxValue)
{
goto Label_0242;
}
goto Label_0201;
}
goto Label_02E9;
}
Label_028A:
population.OutputActivationFunction = EncogFileSection.ParseActivationFunction(dictionary4, "outAct");
if ((((uint) num2) + ((uint) num2)) < 0)
{
goto Label_0BD6;
}
population.Snapshot = EncogFileSection.ParseBoolean(dictionary4, "snapshot");
population.InputCount = EncogFileSection.ParseInt(dictionary4, "inputCount");
population.OutputCount = EncogFileSection.ParseInt(dictionary4, "outputCount");
goto Label_0242;
Label_02E9:
if ((((uint) num2) - ((uint) num)) >= 0)
{
population.YoungBonusAgeThreshhold = EncogFileSection.ParseInt(dictionary4, "youngAgeThreshold");
}
if (0xff != 0)
{
goto Label_016E;
}
Label_030B:
population.NeatActivationFunction = EncogFileSection.ParseActivationFunction(dictionary4, "neatAct");
goto Label_028A;
Label_03AA:
if (!section.SectionName.Equals("NEAT-POPULATION") || !section.SubSectionName.Equals("CONFIG"))
{
goto Label_0023;
}
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
dictionary4 = section.ParseParams();
}
goto Label_030B;
}
Label_0821:
if (section.SectionName.Equals("NEAT-POPULATION"))
{
if (section.SubSectionName.Equals("GENOMES"))
{
NEATGenome genome = null;
using (IEnumerator<string> enumerator3 = section.Lines.GetEnumerator())
{
string str3;
IList<string> list3;
NEATGenome genome2;
NEATNeuronGene gene;
NEATNeuronGene gene2;
NEATLinkGene gene3;
goto Label_0402;
Label_03DA:
genome.Links.Add(gene3);
goto Label_0402;
Label_03EA:
if (list3[0].Equals("l", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_04EA;
}
Label_0402:
if (enumerator3.MoveNext())
{
goto Label_0770;
}
if ((((uint) num2) | 0x80000000) != 0)
{
goto Label_0023;
}
Label_0429:
gene3.Enabled = int.Parse(list3[2]) > 0;
Label_0440:
gene3.Recurrent = int.Parse(list3[3]) > 0;
gene3.FromNeuronID = int.Parse(list3[4]);
gene3.ToNeuronID = int.Parse(list3[5]);
gene3.Weight = CSVFormat.EgFormat.Parse(list3[6]);
gene3.InnovationId = int.Parse(list3[7]);
goto Label_03DA;
Label_04B4:
if ((((uint) num) & 0) != 0)
{
goto Label_03DA;
}
gene3.Id = int.Parse(list3[1]);
goto Label_0429;
Label_04EA:
gene3 = new NEATLinkGene();
goto Label_04B4;
Label_04F6:
gene2.SplitY = CSVFormat.EgFormat.Parse(list3[7]);
Label_050F:
gene = gene2;
genome.Neurons.Add(gene);
if ((((uint) num2) & 0) != 0)
{
goto Label_0782;
}
goto Label_0402;
Label_053D:
gene2.Enabled = int.Parse(list3[3]) > 0;
gene2.InnovationId = int.Parse(list3[4]);
if (0xff == 0)
{
goto Label_050F;
}
gene2.ActivationResponse = CSVFormat.EgFormat.Parse(list3[5]);
gene2.SplitX = CSVFormat.EgFormat.Parse(list3[6]);
goto Label_04F6;
Label_05A7:
gene2.Id = int.Parse(list3[1]);
gene2.NeuronType = StringToNeuronType(list3[2]);
goto Label_053D;
Label_05DA:
if (!list3[0].Equals("n", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_03EA;
}
if (3 == 0)
{
goto Label_0440;
}
gene2 = new NEATNeuronGene();
goto Label_07C8;
Label_0608:
population.Add(genome);
dictionary3[(int) genome.GenomeID] = genome;
if (((uint) num) >= 0)
{
goto Label_0402;
}
goto Label_06B0;
Label_0638:
genome.AmountToSpawn = CSVFormat.EgFormat.Parse(list3[4]);
genome.NetworkDepth = int.Parse(list3[5]);
if ((((uint) num2) | 0x80000000) == 0)
{
goto Label_07AD;
}
if (((uint) num2) < 0)
{
goto Label_0023;
}
genome.Score = CSVFormat.EgFormat.Parse(list3[6]);
goto Label_06F8;
Label_06B0:
genome.GenomeID = int.Parse(list3[1]);
genome.SpeciesID = int.Parse(list3[2]);
genome.AdjustedScore = CSVFormat.EgFormat.Parse(list3[3]);
goto Label_0638;
Label_06F8:
if (3 != 0)
{
goto Label_0608;
}
goto Label_0402;
Label_0704:
genome.Chromosomes.Add(genome.LinksChromosome);
if ((((uint) num2) + ((uint) num2)) >= 0)
{
goto Label_06B0;
}
goto Label_0402;
Label_0737:
if (8 == 0)
{
goto Label_050F;
}
genome = genome2;
genome.Chromosomes.Add(genome.NeuronsChromosome);
if ((((uint) num) - ((uint) num2)) <= uint.MaxValue)
{
goto Label_0704;
}
Label_0770:
str3 = enumerator3.Current;
list3 = EncogFileSection.SplitColumns(str3);
Label_0782:
if (!list3[0].Equals("g", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_05DA;
}
genome2 = new NEATGenome {
NeuronsChromosome = new Chromosome()
};
Label_07AD:
genome2.LinksChromosome = new Chromosome();
goto Label_0737;
Label_07C8:
if ((((uint) num2) - ((uint) num)) <= uint.MaxValue)
{
goto Label_05A7;
}
if (0 == 0)
{
goto Label_04EA;
}
goto Label_04B4;
}
}
if ((((uint) num2) < 0) || ((((uint) num2) - ((uint) num2)) > uint.MaxValue))
{
goto Label_030B;
}
}
goto Label_03AA;
Label_085C:
if (section.SectionName.Equals("NEAT-POPULATION"))
{
if ((((uint) num) | 1) == 0)
{
goto Label_0266;
}
if (section.SubSectionName.Equals("SPECIES"))
{
if ((((uint) num) | 8) == 0)
{
goto Label_0201;
}
using (IEnumerator<string> enumerator2 = section.Lines.GetEnumerator())
{
string str2;
string[] strArray;
BasicSpecies species;
BasicSpecies species2;
goto Label_0913;
Label_08CB:
species = species2;
species.SpawnsRequired = CSVFormat.EgFormat.Parse(strArray[5]);
dictionary2[species] = int.Parse(strArray[6]);
population.Species.Add(species);
dictionary[(int) species.SpeciesID] = species;
Label_0913:
if (enumerator2.MoveNext())
{
goto Label_09D6;
}
goto Label_0023;
Label_0924:
if ((((uint) num2) & 0) != 0)
{
goto Label_0969;
}
if (2 == 0)
{
goto Label_0924;
}
goto Label_09BE;
Label_0941:
species2 = new BasicSpecies();
species2.SpeciesID = int.Parse(strArray[0]);
species2.Age = int.Parse(strArray[1]);
Label_0969:
species2.BestScore = CSVFormat.EgFormat.Parse(strArray[2]);
species2.GensNoImprovement = int.Parse(strArray[3]);
species2.SpawnsRequired = CSVFormat.EgFormat.Parse(strArray[4]);
if ((((uint) num) + ((uint) num2)) >= 0)
{
goto Label_0924;
}
Label_09BE:
if ((((uint) num2) + ((uint) num)) <= uint.MaxValue)
{
goto Label_09FD;
}
Label_09D6:
str2 = enumerator2.Current;
strArray = str2.Split(new char[] { ',' });
goto Label_0941;
Label_09FD:
if ((((uint) num) - ((uint) num)) <= uint.MaxValue)
{
goto Label_08CB;
}
goto Label_0023;
}
}
}
goto Label_0821;
Label_0BD6:
dictionary2 = new Dictionary<ISpecies, int>();
dictionary3 = new Dictionary<int, IGenome>();
goto Label_0023;
}
private void trainNetworkBackprop()
{
// IMLTrain train = new Backpropagation(this.network, this.input,this.ideal, 0.000001, 0.1);
IMLDataSet aset = new BasicMLDataSet(input, ideal);
int epoch = 1;
// train the neural network
ICalculateScore score = new TrainingSetScore(aset);
IMLTrain trainAlt = new NeuralSimulatedAnnealing(network, score, 10, 2, 100);
IMLTrain trainMain = new Backpropagation(network, aset, 0.001, 0.0);
StopTrainingStrategy stop = new StopTrainingStrategy();
var pop = new NEATPopulation(INPUT_SIZE, OUTPUT_SIZE, 1000);
// train the neural network
var step = new ActivationStep();
step.Center = 0.5;
pop.OutputActivationFunction = step;
var train = new NEATTraining(score, pop);
trainMain.AddStrategy(new Greedy());
trainMain.AddStrategy(new HybridStrategy(trainAlt));
trainMain.AddStrategy(stop);
trainMain.AddStrategy(new HybridStrategy(train));
network.ClearContext();
while (!stop.ShouldStop())
{
trainMain.Iteration();
train.Iteration();
Console.WriteLine(@"Training " + @"Epoch #" + epoch + @" Error:" + trainMain.Error+ @" Genetic iteration:"+trainAlt.IterationNumber+ @"neat iteration:"+train.IterationNumber );
epoch++;
}
}
private void Validate(NEATPopulation pop)
{
Assert.AreEqual(10, pop.PopulationSize);
Assert.AreEqual(0.2, pop.SurvivalRate);
// see if the population can actually be used to train
IMLDataSet trainingSet = new BasicMLDataSet(XOR.XORInput, XOR.XORIdeal);
ICalculateScore score = new TrainingSetScore(trainingSet);
IEvolutionaryAlgorithm train = NEATUtil.ConstructNEATTrainer(pop, score);
train.Iteration();
}
/// <summary>
/// Construct a random HyperNEAT genome.
/// </summary>
/// <param name="rnd">Random number generator.</param>
/// <param name="pop">The target population.</param>
/// <param name="inputCount">The input count.</param>
/// <param name="outputCount">The output count.</param>
/// <param name="connectionDensity">The connection densitoy, 1.0 for fully connected.</param>
public HyperNEATGenome(EncogRandom rnd, NEATPopulation pop,
int inputCount, int outputCount,
double connectionDensity)
: base(rnd, pop, inputCount, outputCount, connectionDensity)
{
}
/// <inheritdoc/>
public IMLMethod Decode(NEATPopulation pop, Substrate.Substrate substrate,
IGenome genome)
{
// obtain the CPPN
NEATCODEC neatCodec = new NEATCODEC();
NEATNetwork cppn = (NEATNetwork)neatCodec.Decode(genome);
List<NEATLink> linkList = new List<NEATLink>();
IActivationFunction[] afs = new IActivationFunction[substrate.NodeCount];
IActivationFunction af = new ActivationSteepenedSigmoid();
// all activation functions are the same
for (int i = 0; i < afs.Length; i++)
{
afs[i] = af;
}
double c = this.MaxWeight / (1.0 - this.MinWeight);
BasicMLData input = new BasicMLData(cppn.InputCount);
// First create all of the non-bias links.
foreach (SubstrateLink link in substrate.Links)
{
SubstrateNode source = link.Source;
SubstrateNode target = link.Target;
int index = 0;
foreach (double d in source.Location)
{
input.Data[index++] = d;
}
foreach (double d in target.Location)
{
input.Data[index++] = d;
}
IMLData output = cppn.Compute(input);
double weight = output[0];
if (Math.Abs(weight) > this.MinWeight)
{
weight = (Math.Abs(weight) - this.MinWeight) * c
* Math.Sign(weight);
linkList.Add(new NEATLink(source.ID, target.ID,
weight));
}
}
// now create biased links
input.Clear();
int d2 = substrate.Dimensions;
IList<SubstrateNode> biasedNodes = substrate.GetBiasedNodes();
foreach (SubstrateNode target in biasedNodes)
{
for (int i = 0; i < d2; i++)
{
input.Data[d2 + i] = target.Location[i];
}
IMLData output = cppn.Compute(input);
double biasWeight = output[1];
if (Math.Abs(biasWeight) > this.MinWeight)
{
biasWeight = (Math.Abs(biasWeight) - this.MinWeight) * c
* Math.Sign(biasWeight);
linkList.Add(new NEATLink(0, target.ID, biasWeight));
}
}
// check for invalid neural network
if (linkList.Count == 0)
{
return null;
}
linkList.Sort();
NEATNetwork network = new NEATNetwork(substrate.InputCount,
substrate.OutputCount, linkList, afs);
network.ActivationCycles = substrate.ActivationCycles;
return network;
}