Examples of org.neuroph.nnet.learning.BinaryDeltaRule

org.neuroph.nnet.learning.BinaryDeltaRule
Delta rule learning algorithm for perceptrons with step functions. The difference to Perceptronlearning is that Delta Rule calculates error before the non-lnear step transfer function @author Zoran Sevarac

    Perceptron nnet = new Perceptron(inputNeuronsCount, outputNeuronsCount, transferFunctionType);


                if (learningRule.getName().equals(PerceptronLearning.class.getName()))  {
                    nnet.setLearningRule(new PerceptronLearning());
                } else if (learningRule.getName().equals(BinaryDeltaRule.class.getName())) {
                    nnet.setLearningRule(new BinaryDeltaRule());
                }


    return nnet;
  }

View Full Code Here

    ConnectionFactory.fullConnect(inputLayer, outputLayer);


    // set input and output cells for this network
    NeuralNetworkFactory.setDefaultIO(this);
                
                this.setLearningRule(new BinaryDeltaRule());
    // set appropriate learning rule for this network
//    if (transferFunctionType == TransferFunctionType.STEP) {
//      this.setLearningRule(new BinaryDeltaRule(this));
//    } else if (transferFunctionType == TransferFunctionType.SIGMOID) {
//      this.setLearningRule(new SigmoidDeltaRule(this));

View Full Code Here

TOP

Related Classes of org.neuroph.nnet.learning.BinaryDeltaRule

org.neuroph.nnet.comp.ThresholdNeuron

org.neuroph.nnet.Perceptron

org.neuroph.util.NeuralNetworkFactory

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.