Breeding decision trees using genetic algorithms
Download
Free version
Download the free version of GATREE from here
The free version ONLY restricts the maximum number of generations and the maximum size of the initial population. If you like the free version you are encouraged to get the commercial version to exploit the full potential of this program.
Commercial version
The commercial version is available for €200 (plus VAT). If you are interested in nore than one license, please inquire.
Buy the full windows version here
Student License
If you are a student you can buy an academic license for a reduced price (€30 plus VAT). A prerequisite for this is to validate that you are a student (with your student ID or class enrollment).
Click here for the special student price
Academic Course License
For academic courses on Artificial Intelligence, Optimization Engineering and related ones, there’s a special offer of €500 (plus VAT) for 200 licenses for a period of one year. A prerequisite for this is to provide the course details (course URL or similar evidence).
Click here for the special course price.
Source Code License
This is a special purpose license that is negotiated on a per-case basis. Please inquire.
What is new at Version 2?
Version 2 includes the following enhancements:
* A module to precisely visualize the output decision tree. The tree can be zoomed, traversed and viewed through different angles.
* An option to cross-validate the data set. The number of cross-validation iterations can be set by the user.
* An option to save a log of the different decision trees that are created through evolution.
* Precise rules at every node (including attribute name).
* Numerous minor improvements at every aspect of the program.
Acknowledgements
This program uses the following programs and components:
GALib – Galib is a C++ library of Generic Algorithm Components. For more info visit: http://lancet.mit.edu/ga/
VCG – Visualization of Compiler Graphs – The VCG tool reads a textual and readable specification of a graph and visualizes the graph. If not all positions of nodes are fixed, the tool layouts the graph using several heuristics as reducing the number of crossings, minimizing the size of edges and centering of nodes.For more info visit: http://rw4.cs.uni-sb.de/users/sander/html/gsvcg1.html