Skip to content

Meteorite-J/Visual-Machine-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Visual-Machine-Learning

This is a game and visualization project that shows the decision boundaries generated by different machine learning algorithms. Currently it only illustrates two algorithms - pegasos, the primal estimated sub-Gradient solver for SVM, and a multi-layer nerual network. additional features might be added later on.

About the Game

You can play the game here.

As you noticed, each algorithm's page contains a 2D canvas such that new data points can be added and the boundary of a particular algorithm is adjusted accordingly each time you add a new point. You can add white data points by clicking your mouse and add black data points by shift-clicking your moust. Each point is an entry of the dataset that we are going to use to run the algorithms. The color of each point represents its classification label, and the x-y coordinates are its features (i.e. areas near white points are more likely to be classified as white, and areas near black points are more likely to be classified as black).

Additionally, there are two papers I found explains the two algorithms really well. Please do read them if you would like to further explore:

About

web-based educational game that illustrates simple machine learning algorithms

Resources

Stars

Watchers

Forks

Packages

No packages published