Computational Intelligence 1(1):1-10

NON-VON is a massively parallel machine constructed using custom VLSI chips, each containing a number of simple processing elements A preliminary prototype is now operational at Columbia University The machine is intended to provide highly efficient support for a wide range of artificial intelligence and other symbolic applications This paper briefly describes the current version of the NON-VON machine and presents evidence for its applicability to the execution of OPS5 production systems, a number of low-and intermediate-level computer vision tasks, and certain "difficult" relational algebraic operations relevant to knowledge base management Analytic and simulation results are presented for a number of algorithms The data suggest that NON-VON could provide a performance improvement of as much as two to three orders of magnitude over a conventional sequential machine for a wide range of AI tasks

In Defense of Probability Peter Cheeseman SRI International 333 Ravenswood Ave., Menlo Park, California 94025 Abstract In this paper, it is argued that probability theory, when used correctly, is suffrcient for the task of reasoning under uncertainty. Since numerous authors have rejected probability as inadequate for various reasons, the bulk of the paper is aimed at refuting these claims and indicating the scources of error. In particular, the definition of probability as a measure of belief rather than a frequency ratio is advocated, since a frequency interpretation of probability drastically restricts the domain of applicability. Other sources of error include the confusion between relative and absolute probability, the distinction between probability and the uncertainty of that probability. Also, the interaction of logic and probability is discusses and it is argued that many extensions of logic, such as "default logic" are better understood in a probabilistic framework. The main claim of this paper is that the numerous schemes for representing and reasoning about uncertainty that have appeared in the AI literature are unnecessary--probability is all that is needed. 1 Introduction A glance through any major AI publication shows that an overwhelming proportion of papers are concerned with what might be described as the logical approach to inference and knowledge representation. It now widely accepted that many knowledge representations can be mapped into (first order) predicate calculus, and the corresponding inference procedures can be reduced to a type of controlled logical deduction. However, examples of human reasoning (judgements) are full of such terms as "probably", "most", "usually" etc., showing that many patterns of human reasoning are not logical in form, but intrinsically probabilistic. The claim that many patterns of human reasoning are probabilistic does not mean that the underlying "logic" of such patterns cannot be axiomatized. On the contrary, a basis for such an axiomatization is given in section 3. The claim is that when such an exercise is performed, the resulting patterns of inference are different in form from those found in analogous logical deductions.

AI Magazine, 6(4):65-85

A frame-based representation facility contributes to a knowledge system's A fundamental observation arising from work in artificial intelligence (AI) has been that expertise in a task domain requires substantial knowledge about that domain. Domain knowledge typically has many forms, including descriptive definitions of domain-specific terms (e.g., "power plant," "pump, " "flow," "pressure"), descriptions of individual domain objects and their relationships to each other ('e.g.,"Pl is a pump whose pressure is 230 psi"), and criteria for making decisions (e.g., "If the feedwater pump pressure exceeds 400 psi, then close the pump's input value"). Because of this emphasis on representatbon and domain knowledge, systems that use AI techniqules to achieve expertise are often referred to as knowledge-based systems, or simply as knowledge systems. In order for a knowledge system to use domainspecific knowledge, it must have a language for representing that knowledge. The predicate calculus was appealing because of its very general expressive power and well-defined se-. However, because the language constructs are very fine grained and do not provide adequate facilities for defining more complex constructs, domain experts have difficulty using the predicate calculus or understanding knowledge expressed in it.

Addison-Wesley

Proceedings of the 7th Conference of the Cognitive Science Society, University of California, Irvine, CA. pp. 329–334

Review of A Practical Guide to Designing Expert Systems

Letters to the Editor

Canadians have made many contributions to artificial intelligence over the years. This article presents a summary of current research in artificial intelligence in Canada and acquaints readers with the Canadian organization for artificial intelligence -- the Canadian Society for the Computational Studies of Intelligence / Societe Canadienne pour l' Etude de l'Intelligence par Ordinateur (CSCSI/ SCEIO).