// Constructor
public MainForm()
{
InitializeComponent();
// Create network
network = new DistanceNetwork(3, 100 * 100);
// Create map bitmap
mapBitmap = new Bitmap(200, 200, PixelFormat.Format24bppRgb);
//
RandomizeNetwork();
UpdateSettings();
}
// Update map
private void UpdateMap(DistanceNetwork network)
{
// get first layer
Layer layer = network.Layers[0];
// lock
Monitor.Enter(this);
// run through all neurons
for (int i = 0; i < layer.Neurons.Length; i++)
{
Neuron neuron = layer.Neurons[i];
int x = i % networkSize;
int y = i / networkSize;
map[y, x, 0] = (int)neuron.Weights[0];
map[y, x, 1] = (int)neuron.Weights[1];
map[y, x, 2] = 0;
}
// collect active neurons
for (int i = 0; i < pointsCount; i++)
{
network.Compute(trainingSet[i]);
int w = network.GetWinner();
map[w / networkSize, w % networkSize, 2] = 1;
}
// unlock
Monitor.Exit(this);
//
mapPanel.Invalidate();
}
// Worker thread
void SearchSolution()
{
// create network
DistanceNetwork network = new DistanceNetwork(2, networkSize * networkSize);
// set random generators range
foreach (var layer in network.Layers)
foreach (var neuron in layer.Neurons)
neuron.RandGenerator = new UniformContinuousDistribution(
new Range(0, Math.Max(pointsPanel.ClientRectangle.Width, pointsPanel.ClientRectangle.Height)));
// create learning algorithm
SOMLearning trainer = new SOMLearning(network, networkSize, networkSize);
// create map
map = new int[networkSize, networkSize, 3];
double fixedLearningRate = learningRate / 10;
double driftingLearningRate = fixedLearningRate * 9;
// iterations
int i = 0;
// loop
while (!needToStop)
{
trainer.LearningRate = driftingLearningRate * (iterations - i) / iterations + fixedLearningRate;
trainer.LearningRadius = (double)learningRadius * (iterations - i) / iterations;
// run training epoch
trainer.RunEpoch(trainingSet);
// update map
UpdateMap(network);
// increase current iteration
i++;
// set current iteration's info
SetText(currentIterationBox, i.ToString());
// stop ?
if (i >= iterations)
break;
}
// enable settings controls
EnableControls(true);
}
// Worker thread
void SearchSolution()
{
// create network
DistanceNetwork network = new DistanceNetwork(2, neurons);
// set random generators range
foreach (var layer in network.Layers)
foreach (var neuron in layer.Neurons)
neuron.RandGenerator = new UniformContinuousDistribution(new Range(0, 1000));
// create learning algorithm
ElasticNetworkLearning trainer = new ElasticNetworkLearning(network);
double fixedLearningRate = learningRate / 20;
double driftingLearningRate = fixedLearningRate * 19;
// path
double[,] path = new double[neurons + 1, 2];
// input
double[] input = new double[2];
// iterations
int i = 0;
// loop
while (!needToStop)
{
// update learning speed & radius
trainer.LearningRate = driftingLearningRate * (iterations - i) / iterations + fixedLearningRate;
trainer.LearningRadius = learningRadius * (iterations - i) / iterations;
// set network input
int currentCity = rand.Next(citiesCount);
input[0] = map[currentCity, 0];
input[1] = map[currentCity, 1];
// run one training iteration
trainer.Run(input);
// show current path
for (int j = 0; j < neurons; j++)
{
path[j, 0] = network.Layers[0].Neurons[j].Weights[0];
path[j, 1] = network.Layers[0].Neurons[j].Weights[1];
}
path[neurons, 0] = network.Layers[0].Neurons[0].Weights[0];
path[neurons, 1] = network.Layers[0].Neurons[0].Weights[1];
chart.UpdateDataSeries("path", path);
// increase current iteration
i++;
// set current iteration's info
SetText(currentIterationBox, i.ToString());
// stop ?
if (i >= iterations)
break;
}
// enable settings controls
EnableControls(true);
}
