Examples of org.encog.neural.pattern.BAMPattern

org.encog.neural.pattern.BAMPattern
Construct a Bidirectional Access Memory (BAM) neural network. This neural network type learns to associate one pattern with another. The two patterns do not need to be of the same length. This network has two that are connected to each other. Though they are labeled as input and output layers to Encog, they are both equal, and should simply be thought of as the two layers that make up the net.

  
  private static MLMethod createBAM() {
    CreateBAMDialog dialog = new CreateBAMDialog(EncogWorkBench
        .getInstance().getMainWindow());
    if (dialog.process()) {
      BAMPattern bam = new BAMPattern();
      bam.setF1Neurons(dialog.getLayerACount().getValue());
      bam.setF2Neurons(dialog.getLayerBCount().getValue());
      return bam.generate();
    } else
      return null;
  }

View Full Code Here

TOP

Related Classes of org.encog.neural.pattern.BAMPattern

org.encog.neural.bam.BAM

org.encog.workbench.process.CreateNeuralNetwork

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.