private void TrainPersonNeuralNetwork(
Dictionary<Person, List<double[]>[]> trainingMfccs,
Dictionary<Person, List<double[]>[]> testMfccs,
double[] input, double[][] answer, Person person,
PerceptronWrapper network)
{
GnuPlot plot = new GnuPlot(
person.FullName,
@"D:\GIT\nnetwork_mini_pw\charts\plot_" + person.FullName.Replace(' ', '_') + ".png"
);
plot.BeginPlot();
List<double[]>[] personMfccs = null;
int iterations = 0;
while (iterations < MaxIterationCounts) {
double expectedAnswer;
if (Random.NextDouble() < algorithmParams.TCoef) {
expectedAnswer = 0.0d;
Person otherPerson = SelectOtherPerson(person);
personMfccs = trainingMfccs[otherPerson];
}
else {
expectedAnswer = 1.0d;
personMfccs = trainingMfccs[person];
}
DrawInputData(input, personMfccs);
double scale = Math.Sqrt(1.0 + iterations);
double newLearningRate = algorithmParams.LearningRate / scale;
double newMomentum = algorithmParams.Momentum / scale;
answer[0][0] = expectedAnswer;
network.Train(newLearningRate, 1, newMomentum,
new[] { input },
answer);
iterations++;
if (iterations % 1000 == 0) {
double testResult = TestPersonNeuralNetwork(person, testMfccs, input);
double learnResult = TestPersonNeuralNetwork(person, trainingMfccs, input);
AddPlotPoint(plot, iterations, learnResult, testResult);
if (testResult <= TestSetMaxError)
{
break;
}
}
}
plot.AddAlgorithmParamsToTitle(algorithmParams);
plot.End2Plot();
}
private double TestPersonNeuralNetwork(Person testedPerson, Dictionary<Person, List<double[]>[]> testSet, double[] input)
{
PerceptronWrapper network = neuralNetworks[testedPerson];
double error = 0.0;
int testCases = 0;
foreach (Person person in people) {
double answer = (person == testedPerson) ? 1.0 : 0.0;
var personTestSet = testSet[person];
foreach (var testFile in personTestSet) {
var testArray = testFile.ToArray();
for (int inputBegining = 0; inputBegining < testArray.Length - algorithmParams.SignalFramesCount; inputBegining++) {
CopyInputData(input, testArray, inputBegining);
double networkAnswer = network.Compute(new[] { input })[0][0];
if (answer > THRESHOLD || answer < (1.0f - THRESHOLD)) {
error += Math.Pow(answer - networkAnswer, 2.0f);
testCases++;
}
}
}
}
return error / testCases;
}
private static string GetRecognitionPlotFileName(Person person)
{
return @"D:\GIT\nnetwork_mini_pw\charts\rplot_" + person.FullName.Replace(' ', '_') + ".png";
}
/// <summary>
/// Losowo wybiera osobe rozna od przekazanej jako parametr.
/// </summary>
/// <param name="person"></param>
/// <returns></returns>
private Person SelectOtherPerson(Person person)
{
int otherPersonIndex = Random.Next(people.Count);
Person otherPerson = people[otherPersonIndex];
if (otherPerson == person) {
int otherPersonsCount = people.Count - 1;
Debug.Assert(otherPersonsCount >= 1);
int newOtherPersonIndex = otherPersonIndex + Random.Next(otherPersonsCount) + 1;
otherPerson = people[newOtherPersonIndex % people.Count];
}
return otherPerson;
}
private void AddNewPerson()
{
var newPerson = new Person {FirstName = "Neural", SurName = "Network"};
people.Add(newPerson);
People.MoveCurrentTo(newPerson);
}