Examples of ActivationFunction

de.jungblut.math.activation.ActivationFunction
Squashing function interface to provide multiple activation functions, e.G. in the {@link MultilayerPerceptron}. @author thomas.jungblut
eas.simulation.brain.neural.functions.ActivationFunction
Interface modeling the activation function Phi: R=> R of a neuron. Do not confuse with TransferFunction which models the computation of the weighted input of a neuron. (In literature the term transfer function is often referring to the activation function as well.) IMPORTANT: Activation functions are constrained to return values from [0, 1]. @author Lukas König
eas.users.lukas.neuroCEGPM.simpleNeural.activationFunction.ActivationFunction
Interface modeling the activation function Phi: R=> R of a neuron. Do not confuse with TransferFunction which models the computation of the weighted input of a neuron. (In literature the term transfer function is often referring to the activation function as well.) IMPORTANT: Activation functions are constrained to return values from [0, 1]. @author Lukas König
org.dmg.pmml._40.ACTIVATIONFUNCTION
An implementation of the model object 'Vector Dictionary Type'.
The following features are implemented:
- {@link org.dmg.pmml._40.impl.VectorDictionaryTypeImpl#getExtension Extension}
- {@link org.dmg.pmml._40.impl.VectorDictionaryTypeImpl#getVectorFields Vector Fields}
- {@link org.dmg.pmml._40.impl.VectorDictionaryTypeImpl#getVectorInstance Vector Instance}
- {@link org.dmg.pmml._40.impl.VectorDictionaryTypeImpl#getNumberOfVectors Number Of Vectors}
@generated
org.encog.engine.network.activation.ActivationFunction
This interface allows various activation functions to be used with the neural network. Activation functions are applied to the output from each layer of a neural network. Activation functions scale the output into the desired range. Methods are provided both to process the activation function, as well as the derivative of the function. Some training algorithms, particularly back propagation, require that it be possible to take the derivative of the activation function. Not all activation functions support derivatives. If you implement an activation function that is not derivable then an exception should be thrown inside of the derivativeFunction method implementation. Non-derivable activation functions are perfectly valid, they simply cannot be used with every training algorithm.
tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction
@author josh
tv.floe.metronome.deeplearning.neuralnetwork.activation.ActivationFunction

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

    final int toLayerIndex = this.layerIndex[currentLevel];
    final int fromLayerSize = this.layerCounts[currentLevel + 1];
    final int toLayerSize = this.layerFeedCounts[currentLevel];


    final int index = this.weightIndex[currentLevel];
    final ActivationFunction activation = this.flat
        .getActivationFunctions()[currentLevel + 1];


    // handle weights
    int yi = fromLayerIndex;
    for (int y = 0; y < fromLayerSize; y++) {
      final double output = this.layerOutput[yi];
      double sum = 0;
      int xi = toLayerIndex;
      int wi = index + y;
      for (int x = 0; x < toLayerSize; x++) {
        derivative[wi] += output * this.layerDelta[xi];
        sum += this.weights[wi] * this.layerDelta[xi];
        wi += fromLayerSize;
        xi++;
      }


      this.layerDelta[yi] = sum
          * (activation.derivativeFunction(this.layerSums[yi],this.layerOutput[yi]));
      yi++;
    }
  }

View Full Code Here

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

    for (int i = 0; i < activationFunctions.length; i++) {
      if (i > 0) {
        result.append(',');
      }


      final ActivationFunction af = activationFunctions[i];
      if (af instanceof ActivationSigmoid) {
        result.append("ENCOG.ActivationSigmoid.create()");
      } else if (af instanceof ActivationTANH) {
        result.append("ENCOG.ActivationTANH.create()");
      } else if (af instanceof ActivationLinear) {
        result.append("ENCOG.ActivationLinear.create()");
      } else if (af instanceof ActivationElliott) {
        result.append("ENCOG.ActivationElliott.create()");
      } else if (af instanceof ActivationElliott) {
        result.append("ENCOG.ActivationElliott.create()");
      } else {
        throw new AnalystCodeGenerationError(
            "Unsupported activatoin function for code generation: "
                + af.getClass().getSimpleName());
      }


    }
    result.append(']');
    return result.toString();

View Full Code Here

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

   * @return The array of flat activations.
   */
  public int[] createActivations(final FlatNetwork flat) {
    final int[] result = new int[flat.getActivationFunctions().length];
    for (int i = 0; i < flat.getActivationFunctions().length; i++) {
      final ActivationFunction af = flat.getActivationFunctions()[i];


      if (af instanceof ActivationLinear) {
        result[i] = 0;
      } else if (af instanceof ActivationTANH) {
        result[i] = 1;

View Full Code Here

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

    } else {
      name = fn.toLowerCase();
      params = new double[0];
    }


    ActivationFunction af = allocateAF(name);
    
    if( af==null ) {
      return null;
    }


    if (af.getParamNames().length != params.length) {
      throw new EncogError(name + " expected "
          + af.getParamNames().length + ", but " + params.length
          + " were provided.");
    }


    for (int i = 0; i < af.getParamNames().length; i++) {
      af.setParam(i, params[i]);
    }


    return af;
  }

View Full Code Here

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

        MLMethodFactory.PROPERTY_POPULATION_SIZE, false, 1000);
    
    final int cycles = holder.getInt(
        MLMethodFactory.PROPERTY_CYCLES, false, NEATPopulation.DEFAULT_CYCLES);
    
    ActivationFunction af = this.factory.create(
        holder.getString(MLMethodFactory.PROPERTY_AF, false, MLActivationFactory.AF_SSIGMOID));


    NEATPopulation pop = new NEATPopulation(input,output,populationSize);
    pop.reset();
    pop.setActivationCycles(cycles);

View Full Code Here

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

    
    if( network.getLayerCount()<1 ) {
      throw new EncogError("Neural network does not have an output layer.");
    }
    
    ActivationFunction outputFunction = network.getActivation(network.getLayerCount()-1);
    
    double[] d = { -1000, -100, -50 };
    outputFunction.activationFunction(d, 0, d.length);
    
    if( d[0]>0 && d[1]>0 && d[2]>0 ) {
      inputLow=0;
    }

View Full Code Here

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

   * @return The newly created context layer.
   */
  public FreeformLayer createContext(final FreeformLayer source,
      final FreeformLayer target) {
    final double biasActivation = 0.0;
    ActivationFunction activatonFunction = null;


    if (source.getNeurons().get(0).getOutputs().size() < 1) {
      throw new FreeformNetworkError(
          "A layer cannot have a context layer connected if there are no other outbound connections from the source layer.  Please connect the source layer somewhere else first.");
    }

View Full Code Here

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

   *            True if this is a tanh activation, false for sigmoid.
   */
  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

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

    setAdjustedScore(0);
    this.inputCount = inputCount;
    this.outputCount = outputCount;


    // get the activation function
    ActivationFunction af = pop.getActivationFunctions().pickFirst();


    // first bias
    int innovationID = 0;
    NEATNeuronGene biasGene = new NEATNeuronGene(NEATNeuronType.Bias, af,
        inputCount, innovationID++);

View Full Code Here

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


    final NEATInnovation innovation = ((NEATPopulation)getOwner().getPopulation()).getInnovations()
        .findInnovationSplit(from, to);


    // add the splitting neuron
    final ActivationFunction af = ((NEATPopulation)getOwner().getPopulation())
        .getActivationFunctions().pick(new Random());


    target.getNeuronsChromosome().add(
        new NEATNeuronGene(NEATNeuronType.Hidden, af, innovation
            .getNeuronID(), innovation.getInnovationID()));

View Full Code Here

0 1 2 3 4 5

TOP

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.