Kernel supervised learning methods can be unified by utilizing the tools from regularization theory. The duality between regularization and prior leads to interpreting regularizat...
We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and ...
We show that it is possible to extend hidden Markov models to have a countably infinite number of hidden states. By using the theory of Dirichlet processes we can implicitly integ...
Matthew J. Beal, Zoubin Ghahramani, Carl Edward Ra...
Many researchers have used lexical networks and ontologies to mitigate synonymy and polysemy problems in Question Answering (QA), systems coupled with taggers, query classifiers,...
Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information...
Matthew D. Zeiler, Dilip Krishnan, Graham W. Taylo...