In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...
Michael H. Bowling, Alborz Geramifard, David Winga...
We introduce the Ranked Feature Fusion framework for information retrieval system design. Typical information retrieval formalisms such as the vector space model, the bestmatch mo...
Duplicate detection determines different representations of realworld objects in a database. Recent research has considered the use of relationships among object representations t...
It has been shown that people encounter difficulties in using representations and devices designed to assist navigating unfamiliar terrain. Literature review and self-reported vis...