Examples of org.encog.engine.network.flat.FlatNetwork

org.encog.engine.network.flat.FlatNetwork
Implements a flat (vector based) neural network in the Encog Engine. This is meant to be a very highly efficient feedforward, or simple recurrent, neural network. It uses a minimum of objects and is designed with one principal in mind-- SPEED. Readability, code reuse, object oriented programming are all secondary in consideration. Vector based neural networks are also very good for GPU processing. The flat network classes will make use of the GPU if you have enabled GPU processing. See the Encog class for more info.

   * @param network The neuroph network to use.
   */
  public FlatNetworkLearning(NeuralNetwork network) {
    FlatNetworkPlugin plugin = (FlatNetworkPlugin) network
        .getPlugin(FlatNetworkPlugin.class);
    FlatNetwork flat = plugin.getFlatNetwork();
    if (this.flat == null)
      throw new EncogEngineError(
          "This learning rule only works with a network that has a FlatNetworkPlugin attached.");
    init(flat);
  }

View Full Code Here

      if (flatLayer == null)
        return false;
      flatLayers[index++] = flatLayer;
    }


    FlatNetwork flat = new FlatNetwork(flatLayers);
    FlatNetworkPlugin plugin = new FlatNetworkPlugin(flat);
    network.addPlugin(plugin);


    FlatNetworkLearning training = new FlatNetworkLearning(flat);
    network.setLearningRule(training);

View Full Code Here

TOP

Related Classes of org.encog.engine.network.flat.FlatNetwork

org.encog.engine.data.EngineData

org.encog.engine.EncogEngineError

org.encog.engine.network.activation.ActivationFunction

org.encog.engine.network.activation.ActivationSigmoid

org.encog.engine.network.activation.ActivationTANH

org.encog.engine.util.ErrorCalculation

org.neuroph.nnet.flat.FlatNetworkLearning

org.neuroph.nnet.flat.FlatNetworkPlugin

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.