• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

Java ActivationSigmoid类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Java中org.encog.engine.network.activation.ActivationSigmoid的典型用法代码示例。如果您正苦于以下问题:Java ActivationSigmoid类的具体用法?Java ActivationSigmoid怎么用?Java ActivationSigmoid使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。



ActivationSigmoid类属于org.encog.engine.network.activation包,在下文中一共展示了ActivationSigmoid类的10个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Java代码示例。

示例1: createNeuralNetwork

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
private BasicNetwork createNeuralNetwork() {
  BasicNetwork network = new BasicNetwork();

  // input layer
  network.addLayer(new BasicLayer(null, true, inputLayerSize));

  // hidden layer
  network.addLayer(new BasicLayer(new ActivationSigmoid(), true, inputLayerSize / 6));
  network.addLayer(new BasicLayer(new ActivationSigmoid(), true, inputLayerSize / 6 / 4));

  // output layer
  network.addLayer(new BasicLayer(new ActivationSigmoid(), false, outputLayerSize));

  network.getStructure().finalizeStructure();
  network.reset();

  return network;
}
 
开发者ID:RusZ,项目名称:TextClassifier,代码行数:19,代码来源:Classifier.java


示例2: main

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/**
 * The main method.
 * @param args No arguments are used.
 */
public static void main(final String args[]) {

    // create a neural network, without using a factory
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(null,true,2));
    network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
    network.addLayer(new BasicLayer(new ActivationSigmoid(),false,1));
    network.getStructure().finalizeStructure();
    network.reset();

    // create training data
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);

    // train the neural network
    final ResilientPropagation train = new ResilientPropagation(network, trainingSet);

    int epoch = 1;

    do {
        train.iteration();
        System.out.println("Epoch #" + epoch + " Error:" + train.getError());
        epoch++;
    } while(train.getError() > 0.01);
    train.finishTraining();

    // test the neural network
    System.out.println("Neural Network Results:");
    for(MLDataPair pair: trainingSet ) {
        final MLData output = network.compute(pair.getInput());
        System.out.println(pair.getInput().getData(0) + "," + pair.getInput().getData(1)
                + ", actual=" + output.getData(0) + ",ideal=" + pair.getIdeal().getData(0));
    }

    Encog.getInstance().shutdown();
}
 
开发者ID:neo4j-contrib,项目名称:neo4j-ml-procedures,代码行数:40,代码来源:XORHelloWorld.java


示例3: getNetwork

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
private BasicNetwork getNetwork() {
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true, INPUTS.length));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 25));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true, OUTPUTS.length));
    network.getStructure().finalizeStructure();
    network.reset();
    return network;
}
 
开发者ID:Ignotus,项目名称:torcsnet,代码行数:10,代码来源:EncogMLPTrainingTest.java


示例4: BackPropagationNeuralNet

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/** Neural Network structure initialization */
public BackPropagationNeuralNet() {
  iterations = new ArrayList<>();
  errors = new ArrayList<>();
  
  network = new BasicNetwork();
  network.addLayer(new BasicLayer(null, true, 4));
  network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 10));
  network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
  network.getStructure().finalizeStructure();
  network.reset();
  new ConsistentRandomizer(-1, 1, 500).randomize(network);
}
 
开发者ID:Saka7,项目名称:Layer-Classifier,代码行数:14,代码来源:BackPropagationNeuralNet.java


示例5: ResilientPropagationNeuralNet

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/** Neural Network structure initialization */
public ResilientPropagationNeuralNet() {
  iterations = new ArrayList<>();
  errors = new ArrayList<>();
  network = new BasicNetwork();
  network.addLayer(new BasicLayer(null, true, 4));
  network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 10));
  network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
  network.getStructure().finalizeStructure();
  network.reset();
  new ConsistentRandomizer(-1, 1, 500).randomize(network);
}
 
开发者ID:Saka7,项目名称:Layer-Classifier,代码行数:13,代码来源:ResilientPropagationNeuralNet.java


示例6: generateNetwork

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/**
 * Generate basic NN network object
 */
public static BasicNetwork generateNetwork(int in, int hidden, int out) {
    final BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(new ActivationLinear(), true, in));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true, hidden));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), false, out));

    network.getStructure().finalizeStructure();
    network.reset();
    return network;
}
 
开发者ID:ShifuML,项目名称:guagua,代码行数:14,代码来源:NNUtils.java


示例7: initGradient

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
private void initGradient(MLDataSet training, double[] weights) {
    BasicNetwork network = NNUtils.generateNetwork(this.inputs, this.hiddens, this.outputs);
    // use the weights from master
    network.getFlat().setWeights(weights);

    FlatNetwork flat = network.getFlat();
    // copy Propagation from encog
    double[] flatSpot = new double[flat.getActivationFunctions().length];
    for(int i = 0; i < flat.getActivationFunctions().length; i++) {
        flatSpot[i] = flat.getActivationFunctions()[i] instanceof ActivationSigmoid ? 0.1 : 0.0;
    }

    this.gradient = new Gradient(flat, training, flatSpot, new LinearErrorFunction());
}
 
开发者ID:ShifuML,项目名称:guagua,代码行数:15,代码来源:NNWorker.java


示例8: main

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/**
 * The main method.
 * @param args No arguments are used.
 */
public static void main(final String args[]) {

	// create a neural network, without using a factory
	BasicNetwork network = new BasicNetwork();
	network.addLayer(new BasicLayer(null,true,2));
	network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
	network.addLayer(new BasicLayer(new ActivationSigmoid(),false,1));
	network.getStructure().finalizeStructure();
	network.reset();

	// create training data
	MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);

	// train the neural network
	final ResilientPropagation train = new ResilientPropagation(network, trainingSet);

	int epoch = 1;

	do {
		train.iteration();
		System.out.println("Epoch #" + epoch + " Error:" + train.getError());
		epoch++;
	} while(train.getError() > 0.01);
	train.finishTraining();

	// test the neural network
	System.out.println("Neural Network Results:");
	for(MLDataPair pair: trainingSet ) {
		final MLData output = network.compute(pair.getInput());
		System.out.println(pair.getInput().getData(0) + "," + pair.getInput().getData(1)
				+ ", actual=" + output.getData(0) + ",ideal=" + pair.getIdeal().getData(0));
	}

	Encog.getInstance().shutdown();
}
 
开发者ID:encog,项目名称:encog-sample-java,代码行数:40,代码来源:HelloWorld.java


示例9: test

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
public static void test(double[][] inputValues, double[][] outputValues)
{
    NeuralDataSet trainingSet = new BasicNeuralDataSet(inputValues, outputValues);
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 4));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1000));
    network.addLayer(new BasicLayer(new ActivationLinear(), false, 1));
    network.getStructure().finalizeStructure();
    network.reset();
    final Train train = new ResilientPropagation(network, trainingSet);
    int epoch = 1;
    do
    {
        train.iteration();
        System.out.println("Epoch #" + epoch + " Error:" + train.getError());
        epoch++;
    }
    while(epoch < 10000);
    System.out.println("Neural Network Results:");
    for(MLDataPair pair : trainingSet)
    {
        final MLData output = network.compute(pair.getInput());
        System.out.println(pair.getInput().getData(0) + "," + pair.getInput().getData(1) + ", actual="
            + output.getData(0) + ",ideal=" + pair.getIdeal().getData(0));

    }
}
 
开发者ID:santjuan,项目名称:dailyBot,代码行数:28,代码来源:NeuralNetworkAnalysis.java


示例10: newNetwork

import org.encog.engine.network.activation.ActivationSigmoid; //导入依赖的package包/类
/**
 * Create new artificial neural network.
 * 
 * @param inputSize
 *            Size of the input layer.
 * @param hiddenSize
 *            Size of the hidden layer.
 * @param outputSize
 *            Size of the output layer.
 * 
 * @return Neural network created object.
 */
public static BasicNetwork newNetwork(int inputSize, int hiddenSize, int outputSize) {
	BasicNetwork net = new BasicNetwork();

	net.addLayer(new BasicLayer(null, true, inputSize));
	net.addLayer(new BasicLayer(new ActivationSigmoid(), true, hiddenSize));
	net.addLayer(new BasicLayer(new ActivationSigmoid(), false, outputSize));
	net.getStructure().finalizeStructure();
	net.reset();

	return net;
}
 
开发者ID:VelbazhdSoftwareLLC,项目名称:Complica4,代码行数:24,代码来源:Util.java



注:本文中的org.encog.engine.network.activation.ActivationSigmoid类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。


鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
Java PropertyKey类代码示例发布时间:2022-05-22
下一篇:
Java SHA1类代码示例发布时间:2022-05-22
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap