Documentation of 'org.encog.neural.hyperneat.substrate.SubstrateFactory' Java class
SubstrateFactory
org.encog.neural.hyperneat.substrate

Class SubstrateFactory



  • public class SubstrateFactory
    extends java.lang.Object
    Produce substrates for various topologies. Currently provides the sandwich topology. You can create any topology you wish, this is simply a convienance method. ----------------------------------------------------------------------------- http://www.cs.ucf.edu/~kstanley/ Encog's NEAT implementation was drawn from the following three Journal Articles. For more complete BibTeX sources, see NEATNetwork.java. Evolving Neural Networks Through Augmenting Topologies Generating Large-Scale Neural Networks Through Discovering Geometric Regularities Automatic feature selection in neuroevolution
    • Constructor Summary

      Constructors 
      Constructor and Description
      SubstrateFactory() 
    • Method Summary

      All Methods Static Methods Concrete Methods 
      Modifier and Type Method and Description
      static Substrate factorSandwichSubstrate(int inputEdgeSize, int outputEdgeSize)
      Create a sandwich substrate.
      • Methods inherited from class java.lang.Object

        equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • SubstrateFactory

        public SubstrateFactory()
    • Method Detail

      • factorSandwichSubstrate

        public static Substrate factorSandwichSubstrate(int inputEdgeSize,
                                                        int outputEdgeSize)
        Create a sandwich substrate. A sandwich has an input layer connected directly to an output layer, both are square.
        Parameters:
        inputEdgeSize - The input edge size.
        outputEdgeSize - The output edge size.
        Returns:
        The substrate.

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.