/// <summary>
/// Creates an instance of Layer with the specified number of neurons with
/// specified neuron properties
/// </summary>
/// <param name="neuronsCount"> number of neurons in layer </param>
/// <param name="neuronProperties"> properties of neurons in layer </param>
public Layer(int neuronsCount, NeuronProperties neuronProperties) : this(neuronsCount) {
for (int i = 0; i < neuronsCount; i++)
{
Neuron neuron = NeuronFactory.createNeuron(neuronProperties);
this.addNeuron(neuron);
}
}
/// <summary>
/// Create a multilayer perceptron
/// </summary>
/// <param name="layerSizes">Number of neurons per layer</param>
/// <param name="activationFunction">Activation function for every hidden node</param>
/// <param name="outputActivationFunction">Activation function for last layer</param>
/// <param name="regularizationFunction">Regularization function</param>
/// <param name="neuronFactory">Neuron factory used to create neurons</param>
/// <param name="synapseFactory">Synapse factory used to create synapses</param>
/// <returns>New network</returns>
public static Network CreateMultilayerPerceptron(int[] layerSizes, IActivationFunction activationFunction,
IActivationFunction outputActivationFunction, IRegularizationFunction regularizationFunction,
NeuronFactory neuronFactory, SynapseFactory synapseFactory)
{
var prevLayer = new Neuron[layerSizes[0]];
// create input layer
var inputNeurons = new Neuron[layerSizes[0]];
for (var i = 0; i < inputNeurons.Length; i++)
{
var n = neuronFactory.CreateNeuron(activationFunction);
inputNeurons[i] = n;
prevLayer[i] = n;
}
// create hidden layers
for (var i = 1; i < layerSizes.Length - 1; i++)
{
var layer = new Neuron[layerSizes[i]];
for (var j = 0; j < layer.Length; j++)
{
var n = neuronFactory.CreateNeuron(activationFunction);
layer[j] = n;
for (var k = 0; k < prevLayer.Length; k++)
{
var pn = prevLayer[k];
synapseFactory.Link(pn, n, regularizationFunction);
}
}
prevLayer = layer;
}
// create output layer
var outputNeurons = new Neuron[layerSizes[layerSizes.Length - 1]];
for (var i = 0; i < outputNeurons.Length; i++)
{
var outputNeuron = neuronFactory.CreateOutputNeuron(outputActivationFunction);
outputNeurons[i] = outputNeuron;
for (var j = 0; j < prevLayer.Length; j++)
{
var pn = prevLayer[j];
synapseFactory.Link(pn, outputNeuron, regularizationFunction);
}
}
return(new Network {
InputLayer = inputNeurons, OutputLayer = outputNeurons
});
}
public void TestForward()
{
var parameterGenerator = new ActionParameterGenerator(() => 0.1, () => 1.0);
var neuronFactor = new NeuronFactory(parameterGenerator);
var synapseFactory = new SynapseFactory(parameterGenerator);
var n = NetworkFactory.CreateMultilayerPerceptron(new[] { 2, 2, 1 }, ActivationFunction.Sigmoid,
ActivationFunction.Identity, null, neuronFactor, synapseFactory);
var x = new Vector(3, 5);
Assert.IsTrue(Math.Abs(n.Compute(x)[0] - 2.0993931) < 0.001);
}
static void Main(string[] args)
{
var trainDataDirectory = @"D:\Files\Apps\OCR.Server\Resources\TrainData\Samples";
var weightDirectory = @"D:\Files\Apps\OCR.Server\Resources\TrainData\Weights";
var factory = new NeuronFactory();
var service = new NeuronService(weightDirectory, factory);
var recongizeService = new NeuronRecognizeService();
var converter = new RecognitionDataConverter();
var trainDataService = new TrainDataService(trainDataDirectory, converter);
var neuronA = service.Get('A');
foreach (var trainData in trainDataService.Get('A'))
{
Recognize(trainData, neuronA);
}
void Recognize(int[,] trainData, Neuron neuron)
{
if (recongizeService.IsRecognized(trainData, neuron))
{
Console.WriteLine($"Easy! It's [{neuron.Symbol}]. Isn't it? [y/n]: ");
if (Console.ReadLine() != "y")
{
recongizeService.Forget(trainData, neuron);
Recognize(trainData, neuron);
}
return;
}
Console.WriteLine($"Hm... cannot figure out [{neuron.Symbol}]. Lern {neuron.Symbol}? [y/n]");
if (Console.ReadLine() == "y")
{
recongizeService.Learn(trainData, neuron);
Recognize(trainData, neuron);
}
}
}
public void TestBack()
{
var parameterGenerator = new ActionParameterGenerator(() => 0.1, () => 1.0);
var neuronFactor = new NeuronFactory(parameterGenerator);
var synapseFactory = new SynapseFactory(parameterGenerator);
var network = NetworkFactory.CreateMultilayerPerceptron(new[] { 2, 2, 1, 1 }, ActivationFunction.Sigmoid,
ActivationFunction.Identity, null, neuronFactor, synapseFactory);
var networkTrainer = new NetworkTrainer(network);
var x = new Vector(3, 5);
network.Compute(x);
networkTrainer.Back(42.0);
var n = network.OutputLayer[0].Inputs[0].Source;
Console.WriteLine(n.InputDerivative);
Console.WriteLine(n.OutputDerivative);
Console.WriteLine(n.InputDerivativeCount);
Assert.IsTrue(Math.Abs(-3.987764 - n.InputDerivative) < 0.01);
Assert.IsTrue(Math.Abs(-41.009155 - n.OutputDerivative) < 0.01);
Assert.AreEqual(1, n.InputDerivativeCount);
}
public void TestTrainXor()
{
var pg = new PositiveUniformParameterGenerator();
var neuronFactor = new NeuronFactory(pg);
var synapseFactory = new SynapseFactory(pg);
var n = NetworkFactory.CreateMultilayerPerceptron(new[] { 2, 2, 1 }, ActivationFunction.Sigmoid,
ActivationFunction.Identity, null, neuronFactor, synapseFactory);
var trainer = new NetworkTrainer(n, 0.9, 0.1);
var examples = new Matrix(new double[, ] {
{ 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 }
});
var labels = new Vector(0, 1, 1, 0);
trainer.Train(examples, labels, 1000);
for (var i = 0; i < labels.Length; i++)
{
var x = examples.GetRow(i);
var y = labels[i];
Console.WriteLine("Actual: {0}, Result: {1}", y, n.Compute(x));
Assert.IsTrue(Math.Abs(y - n.Compute(x)[0]) < 0.01);
}
}
