Package org.encog.neural.pattern

Examples of org.encog.neural.pattern.FeedForwardPattern

114
115
116
117
118
119
120
121
122
123
124
125
 
 

  public BasicNetwork createFeedForward()
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(this.input[0].length);
    pattern.setOutputNeurons(this.ideal[0].length);
    pattern.addHiddenLayer(8);
    pattern.setActivationFunction(new ActivationSigmoid());
    return (BasicNetwork)pattern.generate();
  }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
    return (BasicNetwork)pattern.generate();
  }

  static BasicNetwork createFeedforwardNetwork() {
    // construct a feedforward type network
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setActivationFunction(new ActivationSigmoid());
    pattern.setInputNeurons(1);
    pattern.addHiddenLayer(2);
    pattern.setOutputNeurons(1);
    return (BasicNetwork)pattern.generate();
  }
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
   * @return The neural network.
   */
  public static BasicNetwork simpleFeedForward(final int input,
      final int hidden1, final int hidden2, final int output,
      final boolean tanh) {
    final FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(input);
    pattern.setOutputNeurons(output);
    if (tanh) {
      pattern.setActivationFunction(new ActivationTANH());
    } else {
      pattern.setActivationFunction(new ActivationSigmoid());
    }

    if (hidden1 > 0) {
      pattern.addHiddenLayer(hidden1);
    }
    if (hidden2 > 0) {
      pattern.addHiddenLayer(hidden2);
    }

    final BasicNetwork network = (BasicNetwork)pattern.generate();
    network.reset();
    return network;
  }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
    return (BasicNetwork)pattern.generate();
  }

  static BasicNetwork createFeedforwardNetwork() {
    // construct a feedforward type network
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setActivationFunction(new ActivationSigmoid());
    pattern.setInputNeurons(1);
    pattern.addHiddenLayer(6);
    pattern.setOutputNeurons(1);
    return (BasicNetwork)pattern.generate();
  }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
    Assert.assertTrue(strategy.shouldStop());
  }
 
  public void testGreedy()
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(1);
    pattern.setOutputNeurons(1);
    BasicNetwork network = (BasicNetwork)pattern.generate();
    MockTrain.setFirstElement(3.0,network);
   
    MockTrain mock = new MockTrain();
    mock.setNetwork(network);
    Greedy strategy = new Greedy();
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    Assert.assertTrue(alt.wasUsed());
  }
 
  public void testReset()
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(1);
    pattern.setOutputNeurons(1);
    BasicNetwork network = (BasicNetwork)pattern.generate();
   
    ResetStrategy strategy = new ResetStrategy(0.95,2);
    MockTrain mock = new MockTrain();
    mock.setNetwork(network);
    mock.addStrategy(strategy);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
    Assert.assertTrue(MockTrain.getFirstElement(network)<20);
  }
 
  public void testSmart()
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(1);
    pattern.setOutputNeurons(1);
    BasicNetwork network = (BasicNetwork)pattern.generate();
   
    SmartLearningRate strategy1 = new SmartLearningRate();
    SmartMomentum strategy2 = new SmartMomentum();
    MockTrain mock = new MockTrain();
    mock.setNetwork(network);
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
public class LunarLander {
 
  public static BasicNetwork createNetwork()
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(3);
    pattern.addHiddenLayer(50);
    pattern.setOutputNeurons(1);
    pattern.setActivationFunction(new ActivationTANH());
    BasicNetwork network = (BasicNetwork)pattern.generate();
    network.reset();
    return network;
  }
View Full Code Here
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
      // decide if entire network is to be recreated
      if ((dialog.getActivationFunctionHidden() != oldActivationHidden)
          || (dialog.getActivationFunctionOutput() != oldActivationOutput)
          || dialog.getHidden().getModel().size() != (network
              .getLayerCount() - 2)) {
        FeedForwardPattern feedforward = new FeedForwardPattern();
        feedforward.setActivationFunction(dialog
            .getActivationFunctionHidden());
        feedforward.setInputNeurons(dialog.getInputCount().getValue());
        for (int i = 0; i < dialog.getHidden().getModel().size(); i++) {
          String str = (String) dialog.getHidden().getModel()
              .getElementAt(i);
          int i1 = str.indexOf(':');
          int i2 = str.indexOf("neur");
          if (i1 != -1 && i2 != -1) {
            str = str.substring(i1 + 1, i2).trim();
            int neuronCount = Integer.parseInt(str);
            feedforward.addHiddenLayer(neuronCount);
          }
        }
        feedforward.setInputNeurons(dialog.getInputCount().getValue());
        feedforward.setOutputNeurons(dialog.getOutputCount().getValue());
        BasicNetwork obj = (BasicNetwork) feedforward.generate();
      } else {
        // try to prune it
        PruneSelective prune = new PruneSelective(network);
        int newInputCount = dialog.getInputCount().getValue();
        int newOutputCount = dialog.getOutputCount().getValue();
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
    return "NeuralNetwork";
  }
 
  public void jsFunction_createFeedForward(int input, int hidden1, int hidden2, int output, String activation)
  {
    FeedForwardPattern pattern = new FeedForwardPattern();
    pattern.setInputNeurons(input);
    pattern.setOutputNeurons(output);
   
    if( hidden1>0 )
      pattern.addHiddenLayer(hidden1);
    if( hidden2>0 )
      pattern.addHiddenLayer(hidden2);
   
    if( activation.equalsIgnoreCase("sigmoid") )
      pattern.setActivationFunction(new ActivationSigmoid());
    else if( activation.equalsIgnoreCase("tanh") )
      pattern.setActivationFunction(new ActivationSigmoid());
    else if( activation.equalsIgnoreCase("linear") )
      pattern.setActivationFunction(new ActivationSigmoid());
    else
      throw new EncogScriptError("Uknown activation type: " + activation);
   
    this.network = pattern.generate();
  }
View Full Code Here
TOP

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

  • org.encog.examples.neural.lunar.LunarLander
  • org.encog.examples.neural.recurrent.elman.ElmanXOR
  • org.encog.examples.neural.recurrent.jordan.JordanXOR
  • org.encog.examples.neural.recurrent.TemporalString
  • org.encog.neural.networks.BasicNetwork
  • org.encog.neural.networks.layers.BasicLayer
  • org.encog.neural.networks.layers.Layer
  • org.encog.neural.networks.training.TestStrategy
  • org.encog.script.javascript.objects.JSNeuralNetwork
  • org.encog.util.simple.EncogUtility
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.