Examples of org.encog.neural.freeform.FreeformNetwork

org.encog.neural.freeform.FreeformNetwork
Implements a freefrom neural network. A freeform neural network can represent much more advanced structures than the flat networks that the Encog BasicNetwork implements. However, while freeform networks are more advanced than the BasicNetwork, they are also much slower. Freeform networks allow just about any neuron to be connected to another neuron. You can have neuron layers if you want, but they are not required.

  public final File EG_FILENAME = TEMP_DIR.createFile("encogtest.eg");
  public final File SERIAL_FILENAME = TEMP_DIR.createFile("encogtest.ser");


  public FreeformNetwork create()
  {
    FreeformNetwork network = XOR.createTrainedFreeformXOR();
    XOR.verifyXOR(network, 0.1);
    
    network.setProperty("test", "test2");


    return network;
  }

View Full Code Here

  }
  
  @Test
  public void testPersistSerial() throws IOException, ClassNotFoundException
  {
    FreeformNetwork network = create();
    
    SerializeObject.save(SERIAL_FILENAME, network);
    FreeformNetwork network2 = (FreeformNetwork)SerializeObject.load(SERIAL_FILENAME);
        
    validate(network2);
  }

View Full Code Here

      return result;
    }


    public static FreeformNetwork createTrainedFreeformXOR() {
      BasicNetwork network = createTrainedXOR();
      return new FreeformNetwork(network);
    }

View Full Code Here

    Assert.assertTrue("Improve rate too low for " + train.getClass().getSimpleName() + 
        ",Improve="+improve+",Needed="+requiredImprove, improve>=requiredImprove);
  }


  public static FreeformNetwork createXORFreeformNetworkUntrained() {
    FreeformNetwork network = new FreeformNetwork();
    FreeformLayer inputLayer = network.createInputLayer(2);
    FreeformLayer hiddenLayer1 = network.createLayer(3);
    FreeformLayer outputLayer = network.createOutputLayer(1);
    
    network.connectLayers(inputLayer, hiddenLayer1, new ActivationSigmoid(), 1.0, false);
    network.connectLayers(hiddenLayer1, outputLayer, new ActivationSigmoid(), 1.0, false);
    
    network.reset(1000);
    return network;
  }

View Full Code Here

TOP

Related Classes of org.encog.neural.freeform.FreeformNetwork

org.encog.engine.network.activation.ActivationFunction

org.encog.engine.network.activation.ActivationTANH

org.encog.mathutil.randomize.ConsistentRandomizer

org.encog.ml.data.basic.BasicMLData

org.encog.ml.data.MLData

org.encog.neural.freeform.task.ConnectionTask

org.encog.neural.freeform.task.NeuronTask

org.encog.neural.networks.BasicNetwork

org.encog.neural.networks.NetworkUtil

org.encog.neural.networks.XOR

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.