public void Test_NeuralNetworkLogic()
{
INeuralNetworkBuilder <double> builder = new SigmoidNeuralNetworkBuilder <GeneticTrainingNeuralNetwork>();
builder.BuildNetwork(2, new int[] { 3 }, 1);
INeuralNetwork <double> network = builder.InitializeNeuralNetworkWithData(
new double[] { 1, 1 },
null,
null);
// First Hidden Layer
network.HiddenLayers.ElementAt(0)[0].Inputs.ElementAt(0).DendriteWeight.Weight = 0.8;
network.HiddenLayers.ElementAt(0)[0].Inputs.ElementAt(1).DendriteWeight.Weight = 0.2;
network.HiddenLayers.ElementAt(0)[1].Inputs.ElementAt(0).DendriteWeight.Weight = 0.4;
network.HiddenLayers.ElementAt(0)[1].Inputs.ElementAt(1).DendriteWeight.Weight = 0.9;
network.HiddenLayers.ElementAt(0)[2].Inputs.ElementAt(0).DendriteWeight.Weight = 0.3;
network.HiddenLayers.ElementAt(0)[2].Inputs.ElementAt(1).DendriteWeight.Weight = 0.5;
// Output Nueron
network.Output.Neurons.ElementAt(0)[0].DendriteWeight.Weight = 0.3;
network.Output.Neurons.ElementAt(0)[0].DendriteWeight.Weight = 0.5;
network.Output.Neurons.ElementAt(0)[0].DendriteWeight.Weight = 0.9;
// Run sigmoid function
network.Pulse(null);
;
}
static void Main(string[] args)
{
INeuralNetworkBuilder <double> builder = new DoubleNeuralNetworkBuilder <BackPropagationNeuralNetwork>();
builder.BuildNetwork(2, new int[] { 10, 20 }, 1); // no hidden layers
INeuralNetwork <double> network = InitializeNeuralNetworkStartingValues(builder);
int iterations = 100;
double[][] input = GetInput(iterations);
double[][] output = GetAdditionOutput(input);
bool countedRight = false;
Random rand = new Random();
int iteration = 1;
while (!countedRight)
{
Console.WriteLine($"Iteration: { iteration }");
for (int i = 0; i < iterations; ++i)
{
(network as BackPropagationNeuralNetwork).Train(input, output);
}
int value1 = rand.Next(10); Console.WriteLine($"Value1 = { value1 }");
int value2 = rand.Next(10); Console.WriteLine($"Value2 = { value2 }");
int sum = value1 + value2; Console.WriteLine($"Sum = { sum }");
network.ApplyLearning(null);
network.Input[0].Value = value1;
network.Input[1].Value = value2;
network.Pulse(null);
double networkOutput = network.Output[0].Value; Console.WriteLine($"Neural Network output value = { networkOutput }");
Console.WriteLine($"End of iteration { iteration }");
Console.WriteLine("============================================================================");
iteration++;
if (sum == networkOutput)
{
countedRight = true;
}
}
Console.ReadKey();
}
static void Main(string[] args)
{
INeuralNetworkBuilder <double> builder = new SigmoidNeuralNetworkBuilder <GeneticTrainingNeuralNetwork>();
builder.BuildNetwork(9, null, 1); // no hidden layers
INeuralNetwork <double> network = builder.InitializeNeuralNetworkWithData(new double[]
{
2, 0, 1,
0, 1, 0,
2, 0, 0
}, null, null);
network.LearningRate = 0.1;
for (int i = 0; i < 10000; ++i)
{
// Calculates Sigmoid Neurons value.
network.Pulse(null);
// Function prepared for Genetic Training of Feed Forward Network
network.ApplyLearning(null);
}
}