public RNA(int capas)
{
// Definiendo el tipo de red.
BackPropNetworkFactory factory = new BackPropNetworkFactory();
//This is an arralist which holds the number of neurons in each layer
ArrayList layers = new ArrayList();
//Cant. de neuronas en la primera capa (capa de entrada)
layers.Add(36);
int i;
for (i = 0; i < capas; i++)
{
//Cant. de capas ocultas
layers.Add(36);
}
//Can. de neuronas en la última capa (capa de salida)
layers.Add(9);
//Creo la red a través del patrón factory
network = factory.CreateNetwork(layers);
}
public Gate()
{
BackPropNetworkFactory factory = new BackPropNetworkFactory();
ArrayList layers = new ArrayList();
layers.Add(16);
layers.Add(16);
layers.Add(16);
layers.Add(10);
Network = factory.CreateNetwork(layers);
}
public static void Demo1()
{
INeuralNetwork nn = new BackPropNetworkFactory().CreateNetwork(new ArrayList(new double[] { 2, 2, 1 }));//instantiate 2-2-1 neural network
TrainingData[] xordata = new TrainingData[] {
new TrainingData(new ArrayList(new double[] { 0, 0 }), new ArrayList(new double[] { 0 })),
new TrainingData(new ArrayList(new double[] { 0, 1 }), new ArrayList(new double[] { 1 })),
new TrainingData(new ArrayList(new double[] { 1, 0 }), new ArrayList(new double[] { 1 })),
new TrainingData(new ArrayList(new double[] { 1, 1 }), new ArrayList(new double[] { 0 }))
}; //the xor table
Console.WriteLine("Training the network:");
for (int i = 0; i < 5000; i++)
{
foreach (TrainingData data in xordata)
{
nn.TrainNetwork(data);
}
drawpbar(i + 1, 5000);
}
bool done = false;
while (!done)
{
Console.WriteLine("Enter two inputs (on new lines) for the neural network! Just press enter once you are done!");
string input = Console.ReadLine();
if (input == "")
{
done = true;
break;
}
else
{
try
{
double i1 = Double.Parse(input);
double i2 = Double.Parse(Console.ReadLine());
Console.WriteLine("Output: " + String.Join(" ", nn.RunNetwork(new ArrayList(new double[] { i1, i2 }))[0]));
}
catch (Exception e)
{
Console.WriteLine("There was an error: " + Environment.NewLine + e);
}
}
}
}
public RNA()
{
BackPropNetworkFactory factory = new BackPropNetworkFactory();
//This is an arralist which holds the number of neurons in each layer
ArrayList layers = new ArrayList();
//Cant. de neuronas en la primera capa (capa de entrada)
layers.Add(36);
//Cant. de neuronas en la primera capa
layers.Add(36);
//Can. de neuronas en la última capa (capa de salida)
layers.Add(9);
//Creo la red a través del patrón factory
network = factory.CreateNetwork(layers);
}
public RNA()
{
BackPropNetworkFactory factory = new BackPropNetworkFactory();
//This is an arralist which holds the number of neurons in each layer
ArrayList layers = new ArrayList();
//Cant. de neuronas en la primera capa (capa de entrada)
layers.Add(36);
//Cant. de neuronas en la capa oculta
layers.Add(36);
//Can. de neuronas en la última capa (capa de salida)
layers.Add(9);
//Creo la red a través del patrón factory
network = factory.CreateNetwork(layers);
//Inicializamos el archivo para guardar las variaciones de Delta y Bias en cada iteracion.
this.initializeLogFiles();
}
/// <summary>
/// Initialize our network for a pixel picture
/// </summary>
public void InitNetwork(Size size)
{
// Example: We are analyzing a 20x20 pixel picture, so let us take the number
// of total inputs as 20 x 20 = 400 neurons
// So let us initialize a 400-400-1 network. I.e, 400 neurons in
// input layer, 400 neurons in hidden layer and 1 neuron in the output
// layer to represent a boolean value
// the factory creates a Backward Propagation Neural Network
BackPropNetworkFactory factory = new BackPropNetworkFactory();
// the arrayList holds the number of neurons in each layer
ArrayList layers = new ArrayList();
// 400 neurons in first layer
layers.Add(size.Width * size.Height);
// 400 neurons in the second layer (the second layer is the first hidden layer)
layers.Add(size.Width * size.Height);
// 1 neurons in the output layer
layers.Add(1);
// provide the arrayList as the parameter, to create a network
_network = factory.CreateNetwork(layers);
_networkInitialized = DateTime.Now;
TotalTrainingRounds.Reset();
}
