We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
This paper describes one solution to the problem of how to select sequence, and link Web resources into a coherent, focused organization for instruction that addresses a user'...
Robert G. Farrell, Soyini D. Liburd, John C. Thoma...
Face alignment seeks to deform a face model to match it with the features of the image of a face by optimizing an appropriate cost function. We propose a new face model that is al...
Visiting museums is an increasingly popular pastime. Studies have shown that visitors can draw on their museum experience, long after their visit, to learn new things in practical ...
Trevor D. Collins, Paul Mulholland, Zdenek Zdr&aac...
Abstract. In this paper, we describe a new way to access information by “chatting” to an information source. This involves a chatbot, a program that emulates human conversation...