public LayerBuilder(int size, int connections, float lr, float mo, ANNOperationsEnum operation, ActivationFunctionEnum activation, EnumOptimizerFunction optmizator)
{
this.size = size;
this.connections = connections;
this.lr = lr;
this.mo = mo;
this.operation = operation;
this.activation = activation;
this.optmizator = optmizator;
}
public static INeuron DenseSigmoid(int connections, int size, float learningRate, float std, EnumOptimizerFunction opt)
{
return(new LayerCreator(size, connections)
.WithLearningRate(learningRate)
.Supervised_f()
.Hidden_f()
.Activation_f()
.Sigmoid_f()
.WithOpetimizator_f(opt)
.FullSynapse(std)
.Build());
}
public static IMultipleNeuron RecurrentTanh(int connections, int size, float learningRate, float std, EnumOptimizerFunction opt)
{
return(new LayerCreator(size, 0)
.WithLearningRate(learningRate)
.Supervised_f()
.Hidden_f()
.MultipleActivator_f(new[] { connections, size })
.TANH_f()
.WithOpetimizator_f(opt)
.FullSynapse(std)
.Build());
}
public LSTMCellModel(int inputSize, int hiddenSize, float learningRate, float std, EnumOptimizerFunction opt)
{
w[0] = BuildedModels.DenseSigmoid(inputSize + hiddenSize, hiddenSize, learningRate, std, opt);
w[1] = BuildedModels.DenseSigmoid(inputSize + hiddenSize, hiddenSize, learningRate, std, opt);
w[2] = BuildedModels.DenseTanh(inputSize + hiddenSize, hiddenSize, learningRate, std, opt);
w[3] = BuildedModels.DenseSigmoid(inputSize + hiddenSize, hiddenSize, learningRate, std, opt);
}
public ClassifierRecurrentNeuralNetwork(int input, int output, int hidden, int units, float learningRate, float std, EnumOptimizerFunction opt)
{
encoder = new RecurrentCellModel();
decoder = new DenseModel();
int x = input;
for (int i = 0; i < units; i++)
{
encoder.AddLayer(BuildedModels.RecurrentTanh(x, hidden, learningRate, std, opt));
x = hidden;
}
decoder.AddLayer(BuildedModels.DenseSoftMax(hidden, output, learningRate, std, opt));
decoder.SetLossFunction(new CrossEntropyLossFunction());
input_size = input;
hidden_size = hidden;
output_size = output;
recurrentUnits = units;
learning_rate = learningRate;
}
public LayerBuilderMultiple WithOpetimizator_f(EnumOptimizerFunction opt)
{
return(new LayerBuilderMultiple(size, connections, lr, mo, operation, activation, opt));
}