We propose a novel method for approximate inference in Bayesian networks (BNs). The idea is to sample data from a BN, learn a latent tree model (LTM) from the data offline, and wh...
This paper addresses the task of automatic classification of semantic relations between nouns. We present an improved WordNet-based learning model which relies on the semantic inf...
This paper describes our experience in using modern Web 2.0 architecture, lightweight Python frameworks, and rapid prototyping to create an AI rostering and workforce management s...
For many machine learning solutions to complex applications, there are significant performance advantages to decomposing the overall task into several simpler sequential stages, c...
Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are us...
Children are facile at both discovering word boundaries and using those words to build higher-level structures in tandem. Current research treats lexical acquisition and grammar i...
ADtrees, a data structure useful for caching sufficient statistics, have been successfully adapted to grow lazily when memory is limited and to update sequentially with an increme...
Robert Van Dam, Irene Langkilde-Geary, Dan Ventura