Torch is a statistical machine learning library written in C++ at IDIAP, currently licensed under GPL, and available through its own website: http://www.Torch.ch. It contains most of the state-of-the-art machine learning algorithms, for both static and dynamic problems, including all sorts of artificial neural networks, support vector machines for regression and classification, Gaussian mixture models, hidden Markov models, Kmeans, K nearest neighbors and Parzen windows. It can also be used to train a connected word speech recognizer. Torch is a research platform that can be quickly updated with novel research ideas and algorithms. Moreover, it has been designed in order to favor efficient implementation.
- Changes to previous version:
Initial Announcement on mloss.org.
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.