private void UpdatePopulation(object sender, EventArgs e)
{
double[][] inputs = new double[tests][];
string[] paths = new string[tests];
double[][] outputs = new double[populationSize * tests][];
NeuralNetwork[] functionPopulation = population.Select(n => n).ToArray();
double[][][][] functionNeuronWeights = allNeuronWeights.Select(n => n).ToArray();
Neuron[][][] functionNeurons = allNeurons.Select(n => n).ToArray();
double[][][] functionInputs = allInputs.Select(n => n).ToArray();
int[] values = new int[tests];
for (int i = 0; i < tests; i++)
{
int place = R.Next(allDigits.Length);
values[i] = allDigits[place].value;
inputs[i] = allDigits[place].pixelValues;
for (int j = 0; j < populationSize; j++)
{
outputs[i * populationSize + j] = new double[10];
}
}
Gpu.Default.For(0, population.Length * tests, i =>
{
outputs[i] = functionPopulation[i / tests].GetOutputs(inputs[i % tests], functionNeuronWeights, functionNeurons, functionInputs);
}
);
for (int i = 0; i < populationSize * tests; i++)
{
NeuralNetwork nn = functionPopulation[i / tests];
nn.sumCost = nn.sumCost + nn.GetCost(values[i % tests], outputs[i]);
nn.testsDone++;
if (nn.MostConfidentOutput(outputs[i]) == values[i % tests])
{
nn.correct++;
}
functionPopulation[i / tests] = nn;
}
population = functionPopulation.Select(n => n).ToArray();
allNeuronWeights = functionNeuronWeights.Select(n => n).ToArray();
allNeurons = functionNeurons.Select(n => n).ToArray();
allInputs = functionInputs.Select(n => n).ToArray();
double[][][][] newNeuronWeights = new double[allNeuronWeights.Length][][][];
Neuron[][][] newNeurons = new Neuron[allNeurons.Length][][];
double[][][] newInputs = new double[allInputs.Length][][];
List <double> grades = new List <double>();
foreach (NeuralNetwork n in population)
{
grades.Add(n.sumCost);
}
Array.Sort(grades.ToArray(), population);
//population = population.Reverse().ToArray();
List <NeuralNetwork> topScorers = new List <NeuralNetwork>();
List <int> order = Randomize(Enumerable.Range(0, populationSize / 2).ToList(), R);
int numRemaining = populationSize / 2;
for (int i = populationSize - 1; i >= 0; i--)
{
if (R.Next(populationSize) >= i || numRemaining == 0)
{
topScorers.Add(population[i]);
}
else
{
numRemaining--;
}
}
topScorers.RemoveRange(0, numRemaining);
List <NeuralNetwork> newPopulation = new List <NeuralNetwork>();
for (int i = 0; newPopulation.Count < populationSize; i++)
{
for (int j = 0; j < 7 && newPopulation.Count < populationSize; j++)
{
if (j >= 2)
{
if (R.Next(order[i]) == 0)
{
newPopulation.Add(new NeuralNetwork(topScorers[order[i]], topScorers[order[(i + j) % order.Count]], newPopulation.Count, newNeuronWeights, newNeurons, newInputs, allNeuronWeights, allNeurons, allInputs));
}
else
{
newPopulation.Add(new NeuralNetwork(topScorers[order[i]], topScorers[order[(i + j) % order.Count]], newPopulation.Count, newNeuronWeights, newNeurons, newInputs, allNeuronWeights, allNeurons, allInputs));
}
}
}
}
best = new NeuralNetwork(population[0], 0, newNeuronWeights, newNeurons, newInputs, allNeuronWeights, allNeurons, allInputs);
newPopulation[0] = best;
population = newPopulation.ToArray();
Array.Copy(newNeuronWeights, allNeuronWeights, 0);
Array.Copy(newNeurons, allNeurons, 0);
Array.Copy(newInputs, allInputs, 0);
scores.Add(((double)best.correct / best.testsDone) * 100);
Invalidate();
}
