Examples of org.encog.neural.networks.layers.BasicLayer

Package org.encog.neural.networks.layers

Examples of org.encog.neural.networks.layers.BasicLayer

org.encog.neural.networks.layers.BasicLayer
Basic functionality that most of the neural layers require. The basic layer is often used by itself to implement forward or recurrent layers. Other layer types are based on the basic layer as well. The following summarizes how basic layers calculate the output for a neural network. Example of a simple XOR network. Input: BasicLayer: 2 Neurons, null biasWeights, null biasActivation Hidden: BasicLayer: 2 Neurons, 2 biasWeights, 1 biasActivation Output: BasicLayer: 1 Neuron, 1 biasWeights, 1 biasActivation Input1Output and Input2Output are both provided. Synapse 1: Input to Hidden Hidden1Activation=(Input1Output Input1->Hidden1Weight) + (Input2Output * Input2->Hidden1Weight) + (HiddenBiasActivation * Hidden1BiasWeight) Hidden1Output=calculate(Hidden1Activation, HiddenActivationFunction) Hidden2Activation=(Input1Output * Input1->Hidden2Weight) + (Input2Output Input2->Hidden2Weight) + (HiddenBiasActivation * Hidden2BiasWeight) Hidden2Output=calculate(Hidden2Activation, HiddenActivationFunction) Synapse 2: Hidden to Output Output1Activation=(Hidden1Output * Hidden1->Output1Weight) + (Hidden2Output Hidden2->Output1Weight) + (OutputBiasActivation * Output1BiasWeight) Output1Output = calculate(Output1Activation, OutputActivationFunction) @author jheaton

    {
        // random matrix data.  However, it provides a constant starting point 
        // for the unit tests.
        
        BasicNetwork network = new BasicNetwork();
        network.addLayer(new BasicLayer(null,true,2));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),false,3));
        network.addLayer(new BasicLayer(null,false,1));
        network.getStructure().finalizeStructure();
        (new NguyenWidrowRandomizer()).randomize( network );
        
        return network;
    }

View Full Code Here

        if (layer.getCount() == 0) {
          throw new EncogError("Layer can't have zero neurons, Unknown architecture element: "
              + architecture + ", can't parse: " + part);
        }


        result.addLayer(new BasicLayer(af, bias,
            layer.getCount()));


      }
    }

View Full Code Here

  public MLMethod generate() {


    if( this.activationOutput==null )
      this.activationOutput = this.activationHidden;
    
    final Layer input = new BasicLayer(null, true,
        this.inputNeurons);


    final BasicNetwork result = new BasicNetwork();
    result.addLayer(input);




    for (final Integer count : this.hidden) {


      final Layer hidden = new BasicLayer(this.activationHidden, true, count);


      result.addLayer(hidden);
    }


    final Layer output = new BasicLayer(this.activationOutput, false,
        this.outputNeurons);
    result.addLayer(output);


    result.getStructure().finalizeStructure();
    result.reset();

View Full Code Here

   * @return The generated network.
   */
  public MLMethod generate() {
    final BasicNetwork network = new BasicNetwork();


    final Layer inputLayer = new BasicLayer(new ActivationLinear(), true,
        this.inputNeurons);
    final Layer outputLayer = new BasicLayer(new ActivationLinear(), false,
        this.outputNeurons);


    network.addLayer(inputLayer);
    network.addLayer(outputLayer);
    network.getStructure().finalizeStructure();

View Full Code Here

0 1 2 3 4

TOP

Related Classes of org.encog.neural.networks.layers.BasicLayer

com.wiieditor.neuralnetwork.NeuralNetworkWrapper

mechanics.NeuralNetwork

org.encog.engine.network.activation.ActivationTANH

org.encog.ensemble.ml.mlp.factory.MultiLayerPerceptronFactory

org.encog.examples.neural.activation.CustomActivation

org.encog.examples.neural.benchmark.MultiBench

org.encog.examples.neural.benchmark.SimpleBenchmark

org.encog.examples.neural.benchmark.TestConverge

org.encog.examples.neural.benchmark.ThreadCount

org.encog.examples.neural.cross.CrossValidateSunspot

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.