Learning structural SVMs with latent variables
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
| Hi-index | 3.84 |
Summary: We present GIMSAN (GIbbsMarkov with Significance ANalysis): a novel tool for de novo motif finding. GIMSAN combines GibbsMarkov, our variant of the Gibbs Sampler, described here for the first time, with our recently introduced significance analysis. Availability: GIMSAN is currently available as a web application and a stand-alone application on Unix and PBS (Portable Batch System) cluster through links from http://www.cs.cornell.edu/~keich. Contact: keich@cs.cornell.edu