private int[] nR = { 1, 1 }; // neighborhood radius
#endregion Fields
#region Constructors
public KohonenLearning(Kohonen nnet)
: base(nnet)
{
LearningRate = 0.9d;
int neuronsNum = this.NeuralNetwork.GetLayerAt(1).NeuronsCount;
mapSize = (int)Math.Sqrt(neuronsNum);
}
/*
* Recupera a estrutura de uma RNA a partir de um arquivo
*/
public static INeuralNetwork NeuralNetworkStructure(string file)
{
string json = ReadFile(file);
ADReNA_API.Util.ExportImportCommon.CommonStructure stru = JsonConvert.DeserializeObject <ADReNA_API.Util.ExportImportCommon.CommonStructure>(json);
INeuralNetwork ann = null;
switch (stru.type)
{
case ExportImportCommon.AnnType.Backpropagation:
ann = new Backpropagation(stru.inputLayerSize.Value, stru.outputLayerSize.Value, stru.hiddenLayerSizes);
((Backpropagation)ann).SetErrorRate(stru.error.Value);
((Backpropagation)ann).SetMaxIterationNumber(stru.iterationNumber.Value);
((Backpropagation)ann).SetLearningRate(stru.learningRate.Value);
break;
case ExportImportCommon.AnnType.Kohonen:
ann = new Kohonen(stru.inputLayerSize.Value, stru.competitiveNeuronLength.Value, stru.maximumWeightRange.Value);
((Kohonen)ann).SetIterationNumber(stru.iterationNumber.Value);
((Kohonen)ann).SetLearningRate(stru.learningRate.Value);
((Kohonen)ann).SetNeighborhoodRadius(stru.neighborhoodRadius.Value);
break;
}
return(ann);
}
static void Main(string[] args)
{
Kohonen kohonen = new Kohonen(3, 40, 40);
}
/// <summary>
/// Creates and returns a new instance of Kohonen network </summary>
/// <param name="inputNeuronsCount"> number of input neurons </param>
/// <param name="outputNeuronsCount"> number of output neurons </param>
/// <returns> instance of Kohonen network </returns>
public static Kohonen createKohonen(int inputNeuronsCount, int outputNeuronsCount)
{
Kohonen nnet = new Kohonen(inputNeuronsCount, outputNeuronsCount);
return(nnet);
}
static void Main(string[] args)
{
Kohonen kohonen = new Kohonen(3, 40, 40);
}
