Examples of org.encog.engine.network.activation.ActivationTANH

Package org.encog.engine.network.activation

Examples of org.encog.engine.network.activation.ActivationTANH

org.encog.engine.network.activation.ActivationTANH
The hyperbolic tangent activation function takes the curved shape of the hyperbolic tangent. This activation function produces both positive and negative output. Use this activation function if both negative and positive output is desired.

    if (dialog.process()) {
      ElmanPattern elman = new ElmanPattern();
      elman.setInputNeurons(dialog.getInputCount().getValue());
      elman.addHiddenLayer(dialog.getHiddenCount().getValue());
      elman.setOutputNeurons(dialog.getOutputCount().getValue());
      elman.setActivationFunction(new ActivationTANH());
      return elman.generate();
    } else
      return null;


  }

View Full Code Here

  }


  private static MLMethod createFeedForward() {
    CreateFeedforward dialog = new CreateFeedforward(EncogWorkBench
        .getInstance().getMainWindow());
    dialog.setActivationFunctionHidden(new ActivationTANH());
    dialog.setActivationFunctionOutput(new ActivationTANH());
    
    if (dialog.process()) {
      FeedForwardPattern feedforward = new FeedForwardPattern();
      feedforward.setActivationFunction(dialog.getActivationFunctionHidden());
      feedforward.setActivationOutput(dialog.getActivationFunctionOutput());

View Full Code Here

  }


  private static BasicNetwork createAutomatic() {
    CreateAutomatic dialog = new CreateAutomatic(EncogWorkBench
        .getInstance().getMainWindow());
    dialog.setActivationFunction(new ActivationTANH());
    
    dialog.getWeightTries().setValue(5);
    dialog.getIterations().setValue(25);
    dialog.getWindowSize().setValue(10);

View Full Code Here

    dialog.setActivationFunctionOutput(oldActivationOutput);
    dialog.getInputCount().setValue(network.getInputCount());
    dialog.getOutputCount().setValue(network.getOutputCount());
    int hiddenLayerCount = network.getLayerCount() - 2;


    ActivationFunction oldActivationHidden = new ActivationTANH();
    for (int i = 0; i < hiddenLayerCount; i++) {
      int num = network.getLayerNeuronCount(i + 1);
      String str = "Hidden Layer " + (i + 1) + ": " + num + " neurons";
      dialog.getHidden().getModel().addElement(str);
    }

View Full Code Here

    if (name.equalsIgnoreCase(MLActivationFactory.AF_STEP)) {
      return new ActivationStep();
    }


    if (name.equalsIgnoreCase(MLActivationFactory.AF_TANH)) {
      return new ActivationTANH();
    }
    
    if( name.equalsIgnoreCase(MLActivationFactory.AF_SSIGMOID)) {
      return new ActivationSteepenedSigmoid();
    }

View Full Code Here

   * @param target
   *            The target layer.
   */
  public void connectLayers(final FreeformLayer source,
      final FreeformLayer target) {
    connectLayers(source, target, new ActivationTANH(), 1.0, false);
  }

View Full Code Here

  public FlatNetwork(final int input, final int hidden1, final int hidden2,
      final int output, final boolean tanh) {


    final ActivationFunction linearAct = new ActivationLinear();
    FlatLayer[] layers;
    final ActivationFunction act = tanh ? new ActivationTANH()
        : new ActivationSigmoid();


    if ((hidden1 == 0) && (hidden2 == 0)) {
      layers = new FlatLayer[2];
      layers[0] = new FlatLayer(linearAct, input,

View Full Code Here

   *
   * @param neuronCount
   *            How many neurons in this layer.
   */
  public BasicLayer(final int neuronCount) {
    this(new ActivationTANH(), true, neuronCount);
  }

View Full Code Here

      final boolean tanh) {
    final FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(input);
    pattern.setOutputNeurons(output);
    if (tanh) {
      pattern.setActivationFunction(new ActivationTANH());
    } else {
      pattern.setActivationFunction(new ActivationSigmoid());
    }


    if (hidden1 > 0) {

View Full Code Here

  }
  
  public void testActivationTemporal()
  {
    TemporalMLDataSet temporal = new TemporalMLDataSet(5,1);
    temporal.addDescription(new TemporalDataDescription(new ActivationTANH(),Type.RAW, true, false));
    temporal.addDescription(new TemporalDataDescription(new ActivationTANH(),Type.RAW, true, false));
    temporal.addDescription(new TemporalDataDescription(new ActivationTANH(),Type.RAW, false, true));
    for(int i=0;i<10;i++)
    {
      TemporalPoint tp = temporal.createPoint(i);
      tp.setData(0, 1.0+(i*3));
      tp.setData(1, 2.0+(i*3));

View Full Code Here

0 1 2

TOP

Related Classes of org.encog.engine.network.activation.ActivationTANH

org.encog.engine.network.flat.FlatNetwork

org.encog.examples.neural.lunar.LunarLander

org.encog.ml.data.temporal.TestTemporal

org.encog.neural.activation.TestActivationTANH

org.encog.neural.flat.FlatNetwork

org.encog.neural.freeform.FreeformNetwork

org.encog.neural.networks.layers.BasicLayer

org.encog.plugin.system.SystemActivationPlugin

org.encog.util.simple.EncogUtility

org.encog.workbench.dialogs.activation.ActivationDialog

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.