Other good options would include logistic regression and random forests. On Wed, Feb 25, 2009 at 6:55 AM, Grant Ingersoll <gsing...@apache.org>wrote:
> Neural nets would be great. I know Ted has expressed an interest in self > organizing maps in the past. > > I think it's all pretty wide open. > > Good luck > Grant > > > > > On Feb 24, 2009, at 11:45, Vladimir Mitrovic <snipe...@gmail.com> wrote: > > Hello everyone, >> >> I'm thinking about applying for this year's Mahout Summer of Code >> adventure, so I was considering the algorithms given on >> http://cwiki.apache.org/MAHOUT/#index-Algorithms. Are there any >> algorithms that are higher on the priority scale for you guys, or the >> community? Any companies or individuals out there using Mahout that >> could benefit from a certain algorithm? >> >> Personally, I'm considering the Neural Network algorithm since I have >> had some experience with NNs before (nothing big though) and have a >> general understanding of their mechanics. >> >> I've read the "Map-Reduce for Machine Learning on Multicore" paper (as >> per your suggestion), and I'd appreciate any feedback that would steer >> my further reading in the right direction. >> >> Thanks, >> Vladimir >> http://snipe714.googlepages.com >> > -- 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)