Skip to content

Cellular Automata Evolution using Genetic Algorithm

Notifications You must be signed in to change notification settings

ashfaq1701/ca-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Cellular Automata Pattern Evolution Using Genetic Algorithms

In this project I implemented two cellular automata implementations.

  1. Game of Life
  2. Wolfram Cellular Automata

Both were developed using common interfaces keeping their interoperability in mind. GameOfLife and WolframCA are the classes where these CA rules have been implemented.

Then using Genetic Algorithm I tried to evolve the GA with a predefined target. The predefined target is a CA state after running the CA for a specific number of states.

Two fitness functions are used while running the GA, MAE and structural similarity.

The GA is implemented using hierarchical classes. The base class is GA. Then both GAGol and GAWolfram contains the specific GA implementations.

Each of these GA classes are used to run their own set of experiments. The Jupyter notebooks associated with game of life and Wolfram cellular automata are in their respective hyperlinked directories.

Two nice animations of evolving game of life and wolfram ca can be found in their hyperlinked locations. They are produce using these notebooks corresponding to game of life and wolfram ca.

The results of all the experiments are exported to this data directory.

Releases

No releases published

Packages

No packages published