Skip to content

README.md

Latest commit

 

History

History
64 lines (56 loc) · 2.59 KB

README.md

File metadata and controls

64 lines (56 loc) · 2.59 KB
Raw

Artificial Intelligence and Machine Learning in javascript

This repo contains some AI and ML experiments, all of them work on any modern web browser.

AI learns how to land a rocket smoothly

This AI controlls a rocket inside a simulation and learns how to land it smoothly using an algorithm called neuroevolution, the below image shows the difference between the Generation Zero and the 1000th.

Generation #0 Generation #1000

ANN learns image filters

an artificial neural network (ANN) learns how to apply Image filters based on a given example. This example uses perceptron with 3 neurons. The below image shows the ANN learning threshold and negative.

Threshold Negative

Tic Tac Toe

In this experiment, an artificial intelligence explores all the possible states of a Tic Tac Toe board, compiling a decision tree, then it is able to plays agains a human , it may win or may draw but it never loses.

tic-tac-toe

Credits

  • synaptic : The javascript architecture-free neural network library for node.js and the browser
  • RequireJS : JavaScript file and module loader
  • TypeScript : A typed superset of JavaScript that compiles to plain JavaScript
  • SVG.js : The lightweight library for manipulating and animating SVG.
  • p2.js : 2D rigid body physics engine written in JavaScript

Contributors