There is a genuine demand for personalization and guidance in learning systems, as well as in general commercial learning systems for the WWW, and further, for the new, emerging S...
Alexandra I. Cristea, Angelo Wentzler, Egbert Heuv...
We show that random DNF formulas, random log-depth decision trees and random deterministic finite acceptors cannot be weakly learned with a polynomial number of statistical queries...
Dana Angluin, David Eisenstat, Leonid Kontorovich,...
The development of natural language processing (NLP) systems that perform machine translation (MT) and information retrieval (IR) has highlighted the need for the automatic recogn...
Most current image retrieval systems and commercial search engines use mainly text annotations to index and retrieve WWW images. This research explores the use of machine learning...
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...