public override void RefreshView(SharpNeatLib.NeuralNetwork.INetwork network)
{
currentBest = network;
if (nw != null)
{
nw.RefreshView(network);
}
viewing = true;
}
public override SharpNeatLib.NeatGenome.NeatGenome generateGenome(SharpNeatLib.NeuralNetwork.INetwork CPPN)
{
if (concentric)
{
return(CPPN.InputNeuronCount == 5 ? generatePerceptronCircle(CPPN, true) : generatePerceptronCircle(CPPN, false));
}
else
{
return(CPPN.InputNeuronCount == 5 ? generatePerceptronPattern(CPPN, true) : generatePerceptronPattern(CPPN, false));
}
}
//public override void RefreshView(SharpNeatLib.NeuralNetwork.INetwork network)
public void RefreshView(SharpNeatLib.NeuralNetwork.INetwork network)
{
if (network.OutputNeuronCount == 1)
{
if (FoodGatherParams.circle)
{
network = FoodGathererNetworkEvaluator.substrate.generateNetwork(network);
}
else
{
network = FoodGathererNetworkEvaluator.substrate.generateNetwork(network);
}
}
connections = ((FloatFastConcurrentNetwork)network).connectionArray;
neurons = ((FloatFastConcurrentNetwork)network).neuronSignalArray;
resolution = FoodGatherParams.resolution;
this.Refresh();
}
public virtual NeatGenome GenerateGenome(SharpNeatLib.NeuralNetwork.INetwork cppnNetwork)
{
ConnectionGeneList connections = new ConnectionGeneList();
int maxIterations = 2 * (cppnNetwork.TotalNeuronCount - (cppnNetwork.InputNeuronCount + cppnNetwork.OutputNeuronCount)) + 1;
// TODO:
maxIterations = Math.Min(maxIterations, 4);
// TODO:
double epsilon = 0.0;
double threshold = HyperNEATParameters.threshold;
double weightRange = HyperNEATParameters.weightRange;
uint biasid = 0u;
uint inputsStart = biasid + (m_useBias ? 1u : 0u);
uint inputsEnd = (uint)(inputsStart + (m_rows * m_cols));
uint outputsStart = inputsEnd;
uint outputsEnd = (uint)(outputsStart + (m_rows * m_cols));
uint firstHiddenStart = outputsEnd;
float[] coordinates = new float[4];
float output;
uint connectionCounter = 0u;
if (m_useBias)
{
// we use the bias neuron on the center, and use the
// 2nd output of the CPPN to compute its weight
coordinates[0] = 0.0f;
coordinates[1] = 0.0f;
// add the bias link to all neurons of the next layer
for (int ni = 0, ncount = m_rows * m_cols; ni < ncount; ni++)
{
int row = (ni / m_cols);
int col = (ni % m_cols);
coordinates[2] = (-1.0f) + (m_colDelta * (col + 0.5f));
coordinates[3] = (-1.0f) + (m_rowDelta * (row + 0.5f));
cppnNetwork.ClearSignals();
cppnNetwork.SetInputSignals(coordinates);
cppnNetwork.RelaxNetwork(maxIterations, epsilon);
for (int li = 0; li < m_numLayers - 1; li++)
{
output = cppnNetwork.GetOutputSignal(li * 2 + 1);
uint lstart = (uint)(firstHiddenStart + li * (m_cols * m_rows));
if (li == m_numLayers - 2)
{
lstart = outputsStart;
}
if (Math.Abs(output) > threshold)
{
float weight = (float)(((Math.Abs(output) - (threshold)) / (1 - threshold)) * weightRange * Math.Sign(output));
connections.Add(new ConnectionGene(connectionCounter++,
biasid, (uint)(lstart + ni), weight));
}
}
}
}
// now add the connections
for (int inpi = 0, inpcount = m_rows * m_cols; inpi < inpcount; inpi++)
{
for (int outi = 0, outcount = m_rows * m_cols; outi < outcount; outi++)
{
int inrow = (inpi / m_cols); int incol = (inpi % m_cols);
int outrow = (outi / m_cols); int outcol = (outi % m_cols);
coordinates[0] = (-1.0f) + (m_colDelta * (incol + 0.5f));
coordinates[1] = (-1.0f) + (m_rowDelta * (inrow + 0.5f));
coordinates[2] = (-1.0f) + (m_colDelta * (outcol + 0.5f));
coordinates[3] = (-1.0f) + (m_rowDelta * (outrow + 0.5f));
cppnNetwork.ClearSignals();
cppnNetwork.SetInputSignals(coordinates);
cppnNetwork.RelaxNetwork(maxIterations, epsilon);
for (int li = 0; li < m_numLayers - 1; li++)
{
output = cppnNetwork.GetOutputSignal(m_useBias ? li * 2 : li);
uint dststart = (uint)(firstHiddenStart + li * (m_cols * m_rows));
if (li == m_numLayers - 2)
{
dststart = outputsStart;
}
uint srcstart = (uint)(firstHiddenStart + (li - 1) * (m_cols * m_rows));
if (li == 0)
{
srcstart = inputsStart;
}
if (Math.Abs(output) > threshold)
{
float weight = (float)(((Math.Abs(output) - (threshold)) / (1 - threshold)) * weightRange * Math.Sign(output));
connections.Add(new ConnectionGene(connectionCounter++,
(uint)(srcstart + inpi), (uint)(dststart + outi), weight));
}
}
}
}
return(new SharpNeatLib.NeatGenome.NeatGenome(0, m_neurons, connections, m_rows * m_cols, m_rows * m_cols));
}
public SharpNeatLib.NeatGenome.NeatGenome GenerateGenome(SharpNeatLib.NeuralNetwork.INetwork network)
{
int maxIterations = 2 * (network.TotalNeuronCount - (network.InputNeuronCount + network.OutputNeuronCount)) + 1;
double epsilon = 0.0;
double threshold = HyperNEATParameters.threshold;
double weightRange = HyperNEATParameters.weightRange;
// store constant ids for later references
uint biasid = 0u;
uint inputsStart = m_useBias ? 1u : 0u;
uint inputsEnd = (uint)(inputsStart + (m_rows * m_cols));
uint bownerStart = inputsEnd;
uint bownerEnd = bownerStart + 1;
uint outputsStart = bownerEnd;
uint outputsEnd = (uint)(outputsStart + (m_rows * m_cols));
float[] coordinates = new float[4];
float output;
uint connectionCounter = 0;
ConnectionGeneList connections = new ConnectionGeneList();
if (false) //(m_useBias)
{
// we use the bias neuron on the center, and use the
// 2nd output of the CPPN to compute its weight
coordinates[0] = 0.0f;
coordinates[1] = 0.0f;
// add the bias link to all output neurons
for (int ni = 0, ncount = m_rows * m_cols; ni < ncount; ni++)
{
int row = (ni / m_cols);
int col = (ni % m_cols);
coordinates[2] = (-1.0f) + (m_colDelta * (col + 0.5f));
coordinates[3] = (-1.0f) + (m_rowDelta * (row + 0.5f));
network.ClearSignals();
network.SetInputSignals(coordinates);
network.RelaxNetwork(maxIterations, epsilon);
output = network.GetOutputSignal(1);
if (Math.Abs(output) > threshold)
{
float weight = (float)(((Math.Abs(output) - (threshold)) / (1 - threshold)) * weightRange * Math.Sign(output));
connections.Add(new ConnectionGene(connectionCounter++, biasid, (uint)(outputsStart + ni), weight));
}
}
}
// now add possible connections between all input output neuron pairs
for (int inpi = 0, inpcount = m_rows * m_cols; inpi < inpcount; inpi++)
{
for (int outi = 0, outcount = m_rows * m_cols; outi < outcount; outi++)
{
int inrow = (inpi / m_cols); int incol = (inpi % m_cols);
int outrow = (outi / m_cols); int outcol = (outi % m_cols);
coordinates[0] = (-1.0f) + (m_colDelta * (incol + 0.5f));
coordinates[1] = (-1.0f) + (m_rowDelta * (inrow + 0.5f));
coordinates[2] = (-1.0f) + (m_colDelta * (outcol + 0.5f));
coordinates[3] = (-1.0f) + (m_rowDelta * (outrow + 0.5f));
network.ClearSignals();
network.SetInputSignals(coordinates);
network.RelaxNetwork(maxIterations, epsilon);
output = network.GetOutputSignal(0);
if (Math.Abs(output) > threshold)
{
float weight = (float)(((Math.Abs(output) - (threshold)) / (1 - threshold)) * weightRange * Math.Sign(output));
connections.Add(new ConnectionGene(connectionCounter++,
(uint)(inputsStart + inpi), (uint)(outputsStart + outi), weight));
}
}
}
// adding the node for ball owner flag
// we use the bias neuron on the center, and use the
// 2nd output of the CPPN to compute its weight
coordinates[0] = 0.0f;
coordinates[1] = 0.0f;
// add the bias link to all output neurons
for (int ni = 0, ncount = m_rows * m_cols; ni < ncount; ni++)
{
int row = (ni / m_cols);
int col = (ni % m_cols);
coordinates[2] = (-1.0f) + (m_colDelta * (col + 0.5f));
coordinates[3] = (-1.0f) + (m_rowDelta * (row + 0.5f));
network.ClearSignals();
network.SetInputSignals(coordinates);
network.RelaxNetwork(maxIterations, epsilon);
output = network.GetOutputSignal(1);
if (Math.Abs(output) > threshold)
{
float weight = (float)(((Math.Abs(output) - (threshold)) / (1 - threshold)) * weightRange * Math.Sign(output));
connections.Add(new ConnectionGene(connectionCounter++, bownerStart, (uint)(outputsStart + ni), weight));
}
}
return(new SharpNeatLib.NeatGenome.NeatGenome(0, m_neurons, connections, m_rows * m_cols, m_rows * m_cols));
}
public SharpNeatLib.NeuralNetwork.INetwork GenerateNetwork(SharpNeatLib.NeuralNetwork.INetwork CPPN)
{
return(GenerateGenome(CPPN).Decode(null));
}
