Connectionists: A software package for boosting

[yoav freund]

Hi All,

If you are looking for a robust implementation of adaboost you might  
be interested in checking out JBOOST:

http://www.cs.ucsd.edu/users/aarvey/jboost/

This implementation support adaboost, logitboost, alternating  
decision trees and boostexter. We are currently working on an  
implementation of NormalBoost, which is yet another boosting algorithm,
we believe NormalBoost has significant advantages over previous  
boosting algorithm for noisy label data, cost-sensitive boosting and  
multi-class problems.

THe software is distributed as GNU open source through source-forge:  
http://sourceforge.net/projects/jboost/

If you are interested in extending jboost please contact Aaron Arvey:  
aarvey at cs.ucsd.edu

Have Fun!
Yoav

---
Prof. Yoav Freund
EBU3B, Room 4126
Dept. of Comp. Sci. & Eng.
http://www.cse.ucsd.edu/~yfreund/
Tel: (858)  534-1668
Email: yfreund at ucsd.edu