Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model selection, we introduce a conceptually similar method to examine the global behavior of a connectionist model, by counting the number and types of response patterns it can simulate. The Markov Chain Monte Carlo-based algorithm that we constructed Þnds these patterns efficiently. We demonstrate the approach using two localist network models of speech perception.

Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model selection, we introduce a conceptually similar method to examine the global behavior of a connectionist model, by counting the number and types of response patterns it can simulate. The Markov Chain Monte Carlo-based algorithm that we constructed Þnds these patterns efficiently. We demonstrate the approach using two localist network models of speech perception.

Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model selection, we introduce a conceptually similar method to examine the global behavior of a connectionist model, by counting the number and types of response patterns it can simulate. The Markov Chain Monte Carlo-based algorithm that we constructed Þnds these patterns efficiently. We demonstrate the approach using two localist network models of speech perception.

How should we decide among competing explanations of a cognitive process given limited observations? The problem of model selection is at the heart of progress in cognitive science. In this paper, Minimum Description Length (MDL) is introduced as a method for selecting among computational models of cognition. We also show that differential geometry provides an intuitive understanding of what drives model selection in MDL. Finally, adequacy of MDL is demonstrated in two areas of cognitive modeling.

How should we decide among competing explanations of a cognitive process given limited observations? The problem of model selection is at the heart of progress in cognitive science. In this paper, Minimum Description Length (MDL) is introduced as a method for selecting among computational models of cognition. We also show that differential geometry provides an intuitive understanding of what drives model selection in MDL. Finally, adequacy of MDL is demonstrated in two areas of cognitive modeling.

How should we decide among competing explanations of a cognitive process given limited observations? The problem of model selection is at the heart of progress in cognitive science. In this paper, Minimum Description Length (MDL) is introduced as a method for selecting among computational models of cognition. We also show that differential geometry provides an intuitive understanding of what drives model selection in MDL. Finally, adequacy of MDL is demonstrated in two areas of cognitive modeling.

Language, vision, and music: What common cognitive patterns underlie our competence in these disparate modes of thought? Language (natural and formal), vision, and music seem to share at best the following attributes: a hierarchical organization of constituents, recursivity, metaphor, the possibility of self-reference, ambiguity, and systematicity. Can we propose the existence of a general symbol system with instantiations in these three modes, or is the only commonality to be found at the level of such entities as cerebral columnar automata?

In science, business, and policymaking--anywhere data are used in prediction--two sorts of problems requiring very different methods of analysis often arise. The first, problems of recognition and classification, concerns learning how to use some features of a system to accurately predict other features of that system. The second, problems of causal discovery, concerns learning how to predict those changes to some features of a system that will result if an intervention changes other features. This book is about the second--much more difficult--type of problem. The contributors discuss recent research and applications using Bayes nets or directed graphic representations, including representations of feedback or "recursive" systems. The book contains a thorough discussion of foundational issues, algorithms, proof techniques, and applications to economics, physics, biology, educational research, and other areas. ISBN 0-262-57124-2 426 pp., bibliography, index Published by AAAI Press - http://www.aaai.org/Press/

This article is a report of the Eighth Ireland Conference on Artificial Intelligence and Cognitive Science (AICS-97), which was run in conjunction with the Irish Machine Vision and Image Processing Conference (IMVIP-97), held at the University of Ulster, Magee College in Derry / Londonderry, Northern Ireland, on 10 to 13 September 1997.

It is a northern European city of 100,000, almost on the border between the Republic of Ireland and Northern Ireland. The local press (The Derry Journal north Derry coast, with beautiful meetings enjoyed themselves and & Belfast Telegraph) and radio (BBC beaches at Benone and Castlenock expressed their congratulations on Northern Ireland) ran a number of and then through Coleraine to the the program and organization. Also, articles leading up to and during the seaside resorts of Portstewart and for the first time, AICS attracted a conference. All plenary invited speaker Portrush. A few kilometers further large number of delegates and papers talks and the panel session went out along the north Antrim coast, we from abroad, including many from on streaming video and audio, stored arrive at the Giants' Causeway and the United Kingdom, Europe, and Sauce!); Gweedore, home of the Clannad and live with the possibility of phonein for Pattern Recognition (IAPR), the They did lie in the areas of evidential reasoning, AICS-97, the Annual Conference of a supreme job.