Package ca.nengo.model.nef.impl

Examples of ca.nengo.model.nef.impl.NEFEnsembleFactoryImpl

101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
    }

    protected Node createNode(ConfigResult prop, String name) {
        try {

            NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
            Integer numOfNeurons = (Integer) prop.getValue(pNumOfNodes);
            Integer dimensions = (Integer) prop.getValue(pDim);

            /*
             * Advanced properties, these may not necessarily be configued, so
             */
            ApproximatorFactory approxFactory = (ApproximatorFactory) prop.getValue(pApproximator);
            NodeFactory nodeFactory = (NodeFactory) prop.getValue(pNodeFactory);
            Sign encodingSign = (Sign) prop.getValue(pEncodingSign);
            Float encodingDistribution = (Float) prop.getValue(pEncodingDistribution);
            Float radius = (Float) prop.getValue(pRadius);
            Float noise = (Float) prop.getValue(pNoise);

            if (nodeFactory != null) {
                ef.setNodeFactory(nodeFactory);
            }

            if (approxFactory != null) {
                ef.setApproximatorFactory(approxFactory);
            }
            if (noise != null) {
                ApproximatorFactory f=ef.getApproximatorFactory();
                if (f instanceof WeightedCostApproximator.Factory) {
                    ((WeightedCostApproximator.Factory)f).setNoise(noise);
                }
            }

            if (encodingSign != null) {
                if (encodingDistribution == null) {
                    encodingDistribution = 0f;
                }
                VectorGenerator vectorGen = new RandomHypersphereVG(true, 1, encodingDistribution);
                if (encodingSign == Sign.Positive) {
                    vectorGen = new Rectifier(vectorGen, true);
                } else if (encodingSign == Sign.Negative) {
                    vectorGen = new Rectifier(vectorGen, false);
                }
                ef.setEncoderFactory(vectorGen);
            }

            if (radius==null) {
                NEFEnsemble ensemble = ef.make(name, numOfNeurons, dimensions);
                return ensemble;
            } else {
                float[] radii=new float[dimensions];
                for (int i=0; i<dimensions; i++) {
                    radii[i]=radius.floatValue();
                }
                NEFEnsemble ensemble = ef.make(name, numOfNeurons, radii);
                return ensemble;
            }
        } catch (StructuralException e) {
          Util.debugMsg("StructuralException: " + e.toString());

View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
  /*
   * Test method for 'ca.nengo.sim.impl.WriteToDiskSimulatorListener'
   */
  public void testBasicWriting() throws StructuralException, SimulationException {
    Network network = new NetworkImpl();
    NEFEnsembleFactory factory = new NEFEnsembleFactoryImpl();
    NEFEnsemble ensemble = factory.make("Ensemble",100,2);
    File file = new File("testWTDSL.csv");
   
    network.addNode(ensemble);
   
    Probe probe = network.getSimulator().addProbe("Ensemble", "X", true);
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
  /*
   * Test method for 'ca.nengo.sim.impl.WriteToDiskSimulatorListener'
   */
  public void testInterval() throws StructuralException, SimulationException, FileNotFoundException {
    Network network = new NetworkImpl();
    NEFEnsembleFactory factory = new NEFEnsembleFactoryImpl();
    NEFEnsemble ensemble = factory.make("Ensemble",100,2);
    File file = new File("testWTDSL.csv");
   
    network.addNode(ensemble);
   
    float interval = 0.005f;
View Full Code Here
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
  public void testAddBias2D() throws StructuralException, SimulationException {
    Network network = new NetworkImpl();
    FunctionInput input = new FunctionInput("input", new Function[]{new IdentityFunction(1, 0)}, Units.UNK);
    network.addNode(input);
    NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
    int n = 300;
    NEFEnsemble pre = ef.make("pre", n, 2);
    pre.addDecodedTermination("input", MU.uniform(2, 1, 1), .005f, false);
    network.addNode(pre);
    network.addProjection(input.getOrigin(FunctionInput.ORIGIN_NAME), pre.getTermination("input"));
    NEFEnsemble post = ef.make("post", n, 2);
    network.addNode(post);
    post.addDecodedTermination("input", MU.I(2), .01f, false);
    Projection p = network.addProjection(pre.getOrigin(NEFEnsemble.X), post.getTermination("input"));

    DecodedOrigin o = (DecodedOrigin) pre.getOrigin(NEFEnsemble.X);
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
138
    Network network = new NetworkImpl();
   
    FunctionInput input = new FunctionInput("input", new Function[]{new SineFunction(5)}, Units.UNK);
    network.addNode(input);
   
    NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
    NEFEnsemble ensemble = ef.make("ensemble", 100, 1);
    ensemble.addDecodedTermination("input", MU.I(1), .005f, false);
    ensemble.collectSpikes(true);
    network.addNode(ensemble);
   
    network.addProjection(input.getOrigin(FunctionInput.ORIGIN_NAME), ensemble.getTermination("input"));
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
        Plotter.plot(current, 0, dt, T, "current");
        Plotter.plot(pattern);

        //      SigmoidNeuronFactory snf = new SigmoidNeuronFactory(new IndicatorPDF(-10, 10), new IndicatorPDF(-1, 1), new IndicatorPDF(100, 200));
        LinearNeuronFactory lnf = new LinearNeuronFactory(new IndicatorPDF(200, 400), new IndicatorPDF(-1, 1), true);
        NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
        ef.setNodeFactory(lnf);

        try {
            NEFEnsemble ensemble = ef.make("test", 20, 1);
            ensemble.addDecodedTermination("input", MU.I(1), .01f, false);
            Plotter.plot(ensemble);

            Network network = new NetworkImpl();
            network.addNode(ensemble);
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
    Function f = new ConstantFunction(1, 1f);
//    Function f = new SineFunction();
    FunctionInput input = new FunctionInput("input", new Function[]{f}, Units.UNK);
    network.addNode(input);
   
    NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
   
    NEFEnsemble integrator = ef.make("integrator", 500, 1, "integrator1", true); 
    network.addNode(integrator);
    integrator.collectSpikes(true);

    Plotter.plot(integrator);
    Plotter.plot(integrator, NEFEnsemble.X);
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
 
  public static void rasterMemoryTest() {
    try {
      Network network = new NetworkImpl();
     
      NEFEnsembleFactory ef = new NEFEnsembleFactoryImpl();
      final NEFEnsemble ensemble = ef.make("ensemble", 200, 1);
      ensemble.collectSpikes(true);
      network.addNode(ensemble);
     
      FunctionInput input = new FunctionInput("input", new Function[]{new ConstantFunction(1, 1)}, Units.UNK);
      network.addNode(input);
View Full Code Here
13
14
15
16
17
18
19
20
21
22
23
24
        float[][] transform = new float[10][];
        for(int i = 0; i < transform.length; i++) {
            transform[i] = new float[]{1.0f, 1.0f, 1.0f};
        }

        NEFEnsembleFactoryImpl ef = new NEFEnsembleFactoryImpl();
        NEFEnsembleImpl c = (NEFEnsembleImpl)ef.make("c", 10, 1);

        LinearExponentialTermination[] nodeterms = new LinearExponentialTermination[10];
        for(int i = 0; i < nodeterms.length; i++) {
            nodeterms[i] = new LinearExponentialTermination(new SpikingNeuron(null, null, 0.0f, 0.0f, null), null, transform[i], 0.0f);
        }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
        {
            transform[i] = new float[]{1.0f, 1.0f, 1.0f};
            newtransform[i] = new float[]{0.0f, 0.0f, 0.0f};
        }

        NEFEnsembleFactoryImpl ef = new NEFEnsembleFactoryImpl();
        NEFEnsembleImpl c = (NEFEnsembleImpl)ef.make("c", 10, 1);

        LinearExponentialTermination[] nodeterms = new LinearExponentialTermination[10];
        for(int i = 0; i < nodeterms.length; i++) {
            nodeterms[i] = new LinearExponentialTermination(new SpikingNeuron(null, null, 0.0f, 0.0f, null), null, transform[i], 0.0f);
        }
View Full Code Here
TOP

Related Classes of ca.nengo.model.nef.impl.NEFEnsembleFactoryImpl

  • ca.nengo.examples.IntegratorExample
  • ca.nengo.io.FileManager
  • ca.nengo.math.impl.IdentityFunction
  • ca.nengo.math.impl.IndicatorPDF
  • ca.nengo.model.impl.NetworkImplTest
  • ca.nengo.model.impl.ProjectionImplTest
  • ca.nengo.model.nef.impl.DecodedOriginTest
  • ca.nengo.model.nef.impl.NEFEnsembleImplTest
  • ca.nengo.model.nef.NEFEnsemble
  • ca.nengo.model.neuron.impl.LIFNeuronFactory
    • 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.