GiniSVM Toolkit v1.2 Available For Download

[SHANTANU CHAKRABARTTY]

The latest version 1.2 of GiniSVM toolkit can be
downloaded from

http://bach.ece.jhu.edu/svm/ginisvm

* The toolkit has additional heuristics to speed up
  training when there are large number of classes.
* Dynamic Time Warping Kernel has been added for
simple tranducer based experiments.

GiniSVM is a multi-class probabilistic regression
machine based on support vector machines that
generates conditional probability estimates as a
solution to its training. GiniSVM probabilities can
directly be used in its approximate form in a
logistic model for other higher-end models.

-------------------------------------------
Shantanu Chakrabartty
Center for Language and Speech Processing
The Johns Hopkins University,
Baltimore, MD - 21218, USA
email: shantanu at jhu.edu
Phone: 1-410-516-7701 
Fax: 1-410-516-5566
--------------------------------------------