just finished reading the 2008 version of the paper and, as you said, it indeed contains very useful testing approaches, although a big part of it is related to regression and not classification, but random forests can be used for regression too (regression forests).
BART seems powerful, but I wonder if it is not too difficult to implement comparing to Random Forests ? I'm saying this because I can't find a no-nose-bleeding algorithm (without a ton of mathematical formulas). --- En date de : Lun 16.3.09, Ted Dunning <ted.dunn...@gmail.com> a écrit : > De: Ted Dunning <ted.dunn...@gmail.com> > Objet: Re: [gsoc] random forests > À: mahout-dev@lucene.apache.org > Date: Lundi 16 Mars 2009, 7h23 > Here is an interesting related paper > that gives some good pointers for > testing (and an alternative related approach) > > http://www-stat.wharton.upenn.edu/~edgeorge/Research_papers/*BART* > %206--06.pdf<http://www-stat.wharton.upenn.edu/%7Eedgeorge/Research_papers/BART%206--06.pdf> > > or > > http://www-stat.wharton.upenn.edu/~edgeorge/Research_papers/*BART* > %20June%2008.pdf<http://www-stat.wharton.upenn.edu/%7Eedgeorge/Research_papers/BART%20June%2008.pdf> > > (these seem to be versions of the same paper). > > On Sun, Mar 15, 2009 at 1:53 AM, deneche abdelhakim <a_dene...@yahoo.fr>wrote: > > > > > I added a page to the wiki that describes how to build > a random forest and > > how to use it to classify new cases. > > > > http://cwiki.apache.org/confluence/display/MAHOUT/Random+Forests > > > > > > > > > > > > > > > -- > Ted Dunning, CTO > DeepDyve > > 111 West Evelyn Ave. Ste. 202 > Sunnyvale, CA 94086 > www.deepdyve.com > 408-773-0110 ext. 738 > 858-414-0013 (m) > 408-773-0220 (fax) >
