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


        flat.setActivationFunctions(new ActivationFunction[flat
            .getLayerCounts().length]);


        for (final String line : section.getLines()) {
          ActivationFunction af = null;
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          
          // if this is a class name with a path, then do not default to inside of the Encog package.
          String name;
          if( cols.get(0).indexOf('.')!=-1 ) {
            name = cols.get(0);
          } else {
            name = "org.encog.engine.network.activation."
                + cols.get(0);
          }
          
          try {
            final Class<?> clazz = Class.forName(name);
            af = (ActivationFunction) clazz.newInstance();
          } catch (final ClassNotFoundException e) {
            throw new PersistError(e);
          } catch (final InstantiationException e) {
            throw new PersistError(e);
          } catch (final IllegalAccessException e) {
            throw new PersistError(e);
          }


          for (int i = 0; i < af.getParamNames().length; i++) {
            af.setParam(i,
                CSVFormat.EG_FORMAT.parse(cols.get(i + 1)));
          }


          flat.getActivationFunctions()[index++] = af;
        }

View Full Code Here

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

          } else if (cols.get(0).equalsIgnoreCase("n")) {
            final NEATNeuronGene neuronGene = new NEATNeuronGene();
            final int geneID = Integer.parseInt(cols.get(1));
            neuronGene.setId(geneID);


            final ActivationFunction af = EncogFileSection
                .parseActivationFunction(cols.get(2));
            neuronGene.setActivationFunction(af);


            neuronGene.setNeuronType(PersistNEATPopulation
                .stringToNeuronType(cols.get(3)));

View Full Code Here

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


    if (pop.isHyperNEAT()) {
      out.writeProperty(NEATPopulation.PROPERTY_NEAT_ACTIVATION,
          PersistNEATPopulation.TYPE_CPPN);
    } else {
      final ActivationFunction af = pop.getActivationFunctions()
          .getList().get(0).getObj();
      out.writeProperty(NEATPopulation.PROPERTY_NEAT_ACTIVATION, af);
    }


    out.writeProperty(PersistConst.INPUT_COUNT, pop.getInputCount());

View Full Code Here

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


        flat.setActivationFunctions(new ActivationFunction[flat
            .getLayerCounts().length]);


        for (final String line : section.getLines()) {
          ActivationFunction af = null;
          final List<String> cols = EncogFileSection
              .splitColumns(line);
          final String name = "org.encog.engine.network.activation."
              + cols.get(0);
          try {
            final Class<?> clazz = Class.forName(name);
            af = (ActivationFunction) clazz.newInstance();
          } catch (final ClassNotFoundException e) {
            throw new PersistError(e);
          } catch (final InstantiationException e) {
            throw new PersistError(e);
          } catch (final IllegalAccessException e) {
            throw new PersistError(e);
          }


          for (int i = 0; i < af.getParamNames().length; i++) {
            af.setParam(i,
                CSVFormat.EG_FORMAT.parse(cols.get(i + 1)));
          }


          flat.getActivationFunctions()[index++] = af;
        }

View Full Code Here

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

   */
  private Randomizer getRandomizer() {
    boolean useNWR = true;
    
    for(int i=0;i<this.getLayerCount();i++) {
      ActivationFunction af = getActivation(i);
      if( af.getClass()!=ActivationSigmoid.class 
          && af.getClass()!=ActivationTANH.class
          && af.getClass()!=ActivationElliott.class
          && af.getClass()!=ActivationElliottSymmetric.class) {
        useNWR = false;
      }
    }
    
    if (getLayerCount() < 3) {

View Full Code Here

Examples of tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction

        neuron.setError( 0 );
                x++;
        continue;
      }
      
      ActivationFunction transferFunction = neuron.getActivationFunction();
      double neuronInput = neuron.getNetInput();
      double delta = outputError[ x ] * transferFunction.getDerivative( neuronInput ); // delta = (d-y)*df(net)
      neuron.setError( delta );
                        
      this.updateNeuronWeights( neuron );        
      x++;

View Full Code Here

Examples of tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction

        neuron.setError( 0 );
                x++;
        continue;
      }
      
      ActivationFunction transferFunction = neuron.getActivationFunction();
      double neuronInput = neuron.getNetInput();
      double delta = outputError[ x ] * transferFunction.getDerivative( neuronInput ); // delta = (d-y)*df(net)
      neuron.setError( delta );
                        
      this.updateNeuronWeights( neuron );        
      x++;

View Full Code Here

Examples of tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction

      
    } // for


    
    
    ActivationFunction transferFunction = neuron.getActivationFunction();
    
    
    double netInput = neuron.getNetInput(); // should we use input of this or other neuron?
    double fnDerv = transferFunction.getDerivative(netInput);
    double neuronError = fnDerv * deltaSum;
    return neuronError;
  }

View Full Code Here

Examples of tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction

  
  
  public static Neuron createNeuron(Config c, int layerIndex) {
    
    Neuron n = null; 
    ActivationFunction tf = null;
    
    if (0 == layerIndex) {
      n = new InputNeuron();
      
    } else {

View Full Code Here

Examples of tv.floe.metronome.classification.neuralnetworks.activation.ActivationFunction

  
  
  public static Neuron createNeuron(Config c, int layerIndex) {
    
    Neuron n = null; 
    ActivationFunction tf = null;
    
    if (0 == layerIndex) {
      n = new InputNeuron();
      
    } else {

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.