public MainWindow()
{
InitializeComponent();
_xboxDataProvider = new XboxJoystickDataProvider();
_network = Network.Load(NeuronWeightsGenerator.Program.NetworkFile);
if (!ConnectDevice())
{
_timer.Elapsed += (sender, args) => ConnectDevice();
_timer.Start();
}
}
public void Train()
{
var samples = GenerateSamples(category.Compositions);
double[][] inputs = new double[samples.Length][];
double[][] outputs = new double[samples.Length][];
for (int i = 0; i < samples.Length; i++)
{
inputs[i] = samples[i].Inputs;
outputs[i] = samples[i].Outputs;
}
// Create a Bernoulli activation function
//var function = new BernoulliFunction(alpha: 0.5);
var function = new SigmoidFunction(2);
// Create a Restricted Boltzmann Machine for 6 inputs and with 1 hidden neuron
//network = new RestrictedBoltzmannMachine(function, inputsCount: MAX_INPUTS, hiddenNeurons: MAX_OUTPUTS);
network = new ActivationNetwork(function, MAX_INPUTS, 11, MAX_OUTPUTS);
// Create the learning algorithm for RBMs
/* var teacher = new ContrastiveDivergenceLearning(network)
{
Momentum = 0.1,
LearningRate = 0.02
};*/
// create neural network
/* network = new ActivationNetwork(
new SigmoidFunction( 2 ),
2, // two inputs in the network
10, // two neurons in the first layer
2 ); // one neuron in the second layer*/
var teacher = new ResilientBackpropagationLearning(network as ActivationNetwork);
// learn 5000 iterations
for (int i = 0; i < Epochs; i++)
{
var e = teacher.RunEpoch(inputs,outputs);
Console.WriteLine("{0} : {1}", i / (double)Epochs * 100, e);
}
Save();
}
public void Load()
{
this.network = ActivationNetwork.Load(SavePath);
}
private static void getStatistics(Network network, FsdParser parser, double threshold,
out int numTradesWon, out int numTradesLost, out double tradeWinRate)
{
numTradesWon = 0;
numTradesLost = 0;
int numSamples = parser.InputVectors.Length;
for (int sampleIdx = 0; sampleIdx < numSamples; sampleIdx++)
{
double[] computed = network.Compute(parser.InputVectors[sampleIdx]);
if (computed[0] > threshold && computed[1] < threshold)
{
// Netzwerk hat "Rise" errechnet
if (parser.OutputVectors[sampleIdx][0] == 1)
{
numTradesWon++;
}
else
{
numTradesLost++;
}
}
else if (computed[1] > threshold && computed[0] < threshold)
{
// Netzwerk hat "Fall" errechnet
if (parser.OutputVectors[sampleIdx][1] == 1)
{
numTradesWon++;
}
else
{
numTradesLost++;
}
}
}
tradeWinRate = (double)numTradesWon / (numTradesWon + numTradesLost);
}
public recognizer(String n)
{
//Set ANN
//_feature f;
this.name = n;
net = Network.Load(n);
//recognizeFeature();
}
