Coder Social home page Coder Social logo

donaldlee2008 / mlp-perceptron-and-multi-layer-perceptron-back-propagation-gui Goto Github PK

View Code? Open in Web Editor NEW

This project forked from timmmgz/mlp-perceptron-and-multi-layer-perceptron-back-propagation-gui

0.0 1.0 0.0 6.08 MB

3 versions of Perceptron: normal Perceptron; Perceptron GUI; Multilayer Perceptron GUI, back propagation,感知机,感知器,BP 神经网络,反向传播,多层感知器,多层感知机

Java 100.00%

mlp-perceptron-and-multi-layer-perceptron-back-propagation-gui's Introduction

Perceptron.java

In this example, dataset are in hyperplane, please select print1Normal(p); or print2SearchBestRate(p); in main()
这个例子的数据集是在超平面,在main函数里请选择 print1Normal(p);或者print2SearchBestRate(p);

PerceptronWithUI.java

This is a 2D Coordinate System example, I don't create test set, just only shows how train set works in a visual way, the program works as picture, the train set is created randomly by default, please choose the screen size(x/yLimit), number of points etc. by yourself
这是一个二维坐标系的例子,我没有打算弄测试集,只是让训练集可视化,训练集是初始随机生成的,可以尝试自己选择屏幕大小,点的数量等等
image

MLP.java

This is Multi-Layer Perception with 2 layers, you could choose the number of neurons in main(), also try to modify the numOfPoints from 0 to 100000

MLP p = new MLP(50);//50 neurons

And choose the shape you want in "public void initializeParameters(int n) {}", just choose one of them.

// createCircle(50, 100, -30);
// createTwoCircle(30, 100, -30, 50, -100, 20);
// createRectangle();
createHeart(2.3, -80, -20);

Let see some result:
About first rectangle example, you may ask why the 4 lines are already surrounding the rectangle, but the modification in prediction panel(bottom panel) looks like it has delay.
Also about two circles example, you may ask why the lines are already surrounding the small circle on right side, but small circle appear so late in prediction panel.
Answer is that is because not only w1 matters(w1 builds the lines), but also w2(w2 decides the importance of each line) matters too! for k layers(k>2) MLP, it is the same idea, w(k) decides the importance of each k-1 hidden layer outputs, the higher k, the better result in prediction panel, but process of training will be much slower! image image image image image image

mlp-perceptron-and-multi-layer-perceptron-back-propagation-gui's People

Contributors

timmmgz avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.