Examples of org.encog.neural.pattern.JordanPattern

org.encog.neural.pattern.JordanPattern
This class is used to generate an Jordan style recurrent neural network. This network type consists of three regular layers, an input output and hidden layer. There is also a context layer which accepts output from the output layer and outputs back to the hidden layer. This makes it a recurrent neural network. The Jordan neural network is useful for temporal input data. The specified activation function will be used on all layers. The Jordan neural network is similar to the Elman neural network. @author jheaton

    return (BasicNetwork)pattern.generate();
  }
    
  public BasicNetwork createJordan()
  {
    JordanPattern pattern = new JordanPattern();
    pattern.setInputNeurons(this.input[0].length);
    pattern.setOutputNeurons(this.ideal[0].length);
    pattern.addHiddenLayer(16);
    pattern.setActivationFunction(new ActivationSigmoid());
    return (BasicNetwork)pattern.generate();
  }

View Full Code Here

 */
public class JordanXOR {


  static BasicNetwork createJordanNetwork() {
    // construct an Jordan type network
    JordanPattern pattern = new JordanPattern();
    pattern.setActivationFunction(new ActivationSigmoid());
    pattern.setInputNeurons(1);
    pattern.addHiddenLayer(6);
    pattern.setOutputNeurons(1);
    return (BasicNetwork)pattern.generate();
  }

View Full Code Here

  }
  
  public void performJordanTest(int input, int hidden, int ideal)
  {
    // we are really just making sure no array out of bounds errors occur
    JordanPattern jordanPattern = new JordanPattern();
    jordanPattern.setInputNeurons(input);
    jordanPattern.addHiddenLayer(hidden);
    jordanPattern.setOutputNeurons(ideal);
    BasicNetwork network = (BasicNetwork)jordanPattern.generate();
    MLDataSet training = RandomTrainingFactory.generate(1000, 5, network.getInputCount(), network.getOutputCount(), -1, 1);
    ResilientPropagation prop = new ResilientPropagation(network,training);
    prop.iteration();
    prop.iteration();    
  }

View Full Code Here


  private static MLMethod createJordan() {
    CreateJordanDialog dialog = new CreateJordanDialog(EncogWorkBench
        .getInstance().getMainWindow());
    if (dialog.process()) {
      JordanPattern jordan = new JordanPattern();
      jordan.setInputNeurons(dialog.getInputCount().getValue());
      jordan.addHiddenLayer(dialog.getHiddenCount().getValue());
      jordan.setOutputNeurons(dialog.getOutputCount().getValue());
      jordan.setActivationFunction(new ActivationTANH());
      return jordan.generate();
    } else
      return null;


  }

View Full Code Here

  }
  
  public void performJordanTest(int input, int hidden, int ideal)
  {
    // we are really just making sure no array out of bounds errors occur
    JordanPattern jordanPattern = new JordanPattern();
    jordanPattern.setInputNeurons(input);
    jordanPattern.addHiddenLayer(hidden);
    jordanPattern.setOutputNeurons(ideal);
    BasicNetwork network = (BasicNetwork)jordanPattern.generate();
    MLDataSet training = RandomTrainingFactory.generate(1000, 5, network.getInputCount(), network.getOutputCount(), -1, 1);
    ResilientPropagation prop = new ResilientPropagation(network,training);
    prop.iteration();
    prop.iteration();    
  }

View Full Code Here

TOP

Related Classes of org.encog.neural.pattern.JordanPattern

org.encog.examples.neural.recurrent.jordan.JordanXOR

org.encog.examples.neural.recurrent.TemporalString

org.encog.neural.networks.BasicNetwork

org.encog.neural.networks.layers.BasicLayer

org.encog.neural.networks.TestSRN

org.encog.workbench.process.CreateNeuralNetwork

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.