We analyze the amount of information needed to carry out model-based recognition tasks, in the context of a probabilistic data collection model, and independently of the recogniti...
Current explanation-based generalization (EBG) techniques can perform badly when the problem being solved involves recursion. Often an infinite series of learned concepts are gene...
This paper describes a model of the emergence and the universal structural tendencies of vowel systems. Both are considered as the result of self-organisation in a population of l...
Abstract--This paper describes an interactive tool for constrained clustering that helps users to select effective constraints efficiently during the constrained clustering process...
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...