A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
We apply Stochastic Meta-Descent (SMD), a stochastic gradient optimization method with gain vector adaptation, to the training of Conditional Random Fields (CRFs). On several larg...
S. V. N. Vishwanathan, Nicol N. Schraudolph, Mark ...
This paper is devoted to the analysis of network approximation in the framework of approximation and regularization theory. It is shown that training neural networks and similar n...
All the languages for querying semistructured data and the web use as an integral part regular expressions. Based on practical observations, finding the paths that satisfy those r...
A simple, robust sliding-window part-of-speech tagger is presented and a method is given to estimate its parameters from an untagged corpus. Its performance is compared to a standa...