Neuroph studio 入门教程[译文]
博客专区 > nickles 的博客 > 博客详情
Neuroph studio 入门教程[译文]
nickles 发表于10个月前
Neuroph studio 入门教程[译文]
  • 发表于 10个月前
  • 阅读 63
  • 收藏 0
  • 点赞 0
  • 评论 0

移动开发云端新模式探索实践 >>>   

 

PERCEPTRON

Perceptron is a simple two layer neural network with several neurons in input layer, and one or more neurons in output layer. All neurons use step transfer function and network can use LMS based learning algorithm such as Perceptron Learning or Delta Rule. This network can be used as a linear classifier, and it can only be applied to linear separable problems.

感知器是一个简单的两层神经网络,在输入层有多个神经元,输出层有一个或多个神经元。所有的神经元都使用阶跃传递函数,网络可以使用基于LMS的学习算法,如感知器学习或delta规则。该网络可用作线性分类器,只适用于线性可分问题。

To create and train Perceptron neural network using Neuroph Studio do the following:

使用Neuroph Studio创建和训练感知器神经网络遵循以下步骤:

  1. Create Neuroph Project.
  2. Create Perceptron network.
  3. Create training set (in main menu choose Training >New Training Set).
  4. Train network
  5. Test trained network

Step 1. Create Neuroph project.

Click File > New Project.

 

Select Neuroph Project, click Next.

 

Enter project name and location, click Finish.

输入项目名称和地址,点击完成

Project is created, now create neural network. 

项目已经创建好了,现在创建神经网络

Step 2. Create Perceptron network.

Click File > New File

 

Select project from Project drop-down menu, select Neural Network file type, click next.

 

Enter network name, select Perceptron network type, click next.

输入网络名称,选择 “感知器网络”类型,点击继续

In new perceptron dialog enter number ofneurons in input (2) and output layer (1) , choose Perceptron Learningand click Create button.

This will create the Perceptron neural network with two neurons in input, and one in output layer. By default, all neurons with Steptransfer functions.

Now we shall train this simple network to learn logical AND function. First we have to create the training set according to AND truth table.

 

Step 3.  To create training set, click File>New File to open Data Set wizard.

 

Select DataSet file type, then click next.

 

Enter training set name, number of inputs andoutputs as shown on picture below and click Finish button.

Then create training set by entering training elements as input and desired output values of neurons in input and outputlayer. Use Add row button to add new elements, and click OK button when finished.

 

Step 4. Training network. To start network training procedure, drag n' drop training set to corresponding field in the network window, and 'Train' button will become enabled in toolbar. Click the 'Train' button to open Set Learning Parameters dialog.

 

In Set Learning parameters dialoguse default learning parameters, and just click the Train button.

 

When the Total Net Error is zero, thetraining is complete.

 

Step 5. After the training is complete, you can test the network for the whole training set by selecting training set to test, and clicking Test button..

 

This will show test results in the new tab.

 

To test single input, use Set Input button. This will open Set Network Input dialog in which you can enter input values for network delimited withspace.

 

The result of network test is shown on picture below. Network learned logical AND function. As we can see the outputneuron has value 1. Test the network to see how it behaves for other input values.

package org.neuroph.samples;

import Java.util.Arrays;
import org.neuroph.core.NeuralNetwork;
import org.neuroph.nnet.Perceptron;
import org.neuroph.core.data.DataSet;
import org.neuroph.core.data.DataSetRow;

/**
* This sample shows how to create, train, save and load simple Perceptron neural network
*/
public class PerceptronSample {

public static void main(String args[]) {

// create training set (logical AND function)
    DataSet trainingSet = new DataSet(2, 1);
    trainingSet.addRow(new DataSetRow(new double[]{0, 0}, new double[]{0}));
    trainingSet.addRow(new DataSetRow(new double[]{0, 1}, new double[]{0}));
    trainingSet.addRow(new DataSetRow(new double[]{1, 0}, new double[]{0}));
    trainingSet.addRow(new DataSetRow(new double[]{1, 1}, new double[]{1}));

   // create perceptron neural network
    NeuralNetwork myPerceptron = new Perceptron(2, 1);

   // learn the training set
   myPerceptron.learn(trainingSet);

   // test perceptron
   System.out.println("Testing trained perceptron");
   testNeuralNetwork(myPerceptron, trainingSet);

   // save trained perceptron
   myPerceptron.save("mySamplePerceptron.nnet");

   // load saved neural network
   NeuralNetwork loadedPerceptron = NeuralNetwork.createFromFile("mySamplePerceptron.nnet");

   // test loaded neural network
   System.out.println("Testing loaded perceptron");
   testNeuralNetwork(loadedPerceptron, trainingSet);

}

public static void testNeuralNetwork(NeuralNetwork nnet, DataSet tset) {

for(DataSetRow dataRow : tset.getRows()) {

  nnet.setInput(dataRow.getInput());
  nnet.calculate();
  double[ ] networkOutput = nnet.getOutput();
  System.out.print("Input: " + Arrays.toString(dataRow.getInput()) );
  System.out.println(" Output: " + Arrays.toString(networkOutput) );

}

}

}

 

PERCEPTRON IN Java CODE

EXTERNAL LINKS

To learn more about the Perceptrons see:

  • 打赏
  • 点赞
  • 收藏
  • 分享
共有 人打赏支持
粉丝 4
博文 39
码字总数 32378
×
nickles
如果觉得我的文章对您有用,请随意打赏。您的支持将鼓励我继续创作!
* 金额(元)
¥1 ¥5 ¥10 ¥20 其他金额
打赏人
留言
* 支付类型
微信扫码支付
打赏金额:
已支付成功
打赏金额: