It can be shown that neural-like networks containing a single hidden layer of nonlinear activation units can learn to do a piece-wise linear partitioning of a feature space [2]. One result of such a partitioning is a complex gradient surface on which decisions about new input stimuli will be made. The generalization, categorization and clustering propenies of the network are therefore detennined by this mapping of input stimuli to this gradient swface in the output space. This gradient swface is a function of the conditional probability distributions of the output vectors given the input feature vectors as well as a function of the error relating the teacher signal and output.

The Fourth Uncertainty in Artificial Intelligence workshop was held 19-21 August 1988. The workshop featured significant developments in application of theories of representation and reasoning under uncertainty. A recurring idea at the workshop was the need to examine uncertainty calculi in the context of choosing representation, inference, and control methodologies. The effectiveness of these choices in AI systems tends to be best considered in terms of specific problem areas. These areas include automated planning, temporal reasoning, computer vision, medical diagnosis, fault detection, text analysis, distributed systems, and behavior of nonlinear systems. Influence diagrams are emerging as a unifying representation, enabling tool development. Interest and results in uncertainty in AI are growing beyond the capacity of a workshop format.

In Lemmer, J. F. and Kanal, L. N. (Eds.), UAI 2, pp. 149–163. Elsevier/North-Holland.

This paper describes a Bayesian technique for unsupervised classification of data and its computer implementation, AutoClass. Given real valued or discrete data, AutoClass determines the most probable number of classes present in the data, the most probable descriptions of those classes, and each object's probability of membership in each class. The program performs as well as or better than other automatic classification systems when run on the same data and contains no ad hoc similarity measures or stopping criteria. AutoClass has been applied to several databases in which it has discovered classes representing previously unsuspected phenomena.

This article examines the direction in which knowledge bases are constructed for diagnosis and decision making. When building an expert system, it is traditional to elicit knowledge from an expert in the direction in which the knowledge is to be applied, namely, from observable evidence toward unobservable hypotheses. However, experts usually find it simpler to reason in the opposite direction-from hypotheses to unobservable evidence-because this direction reflects causal relationships. Therefore, we argue that a knowledge base be constructed following the expert's natural reasoning direction, and then reverse the direction for use. This choice of representation direction facilitates knowledge acquisition in deterministic domains and is essential when a problem involves uncertainty. We illustrate this concept with influence diagrams, a methodology for graphically representing a joint probability distribution. Influence diagrams provide a practical means by which an expert can characterize the qualitative and quantitative relationships among evidence and hypotheses in the apporiate direction. Once constructed, the relationships can easily be reserved into the less intuitive direction in order to perform inference inference and diagnosis. In this way, knowledge acquisition is made cognitively simple; the machine carries the burden of translating the representation.

Chapman and Hall. See also: Influence diagrams for Bayesian decision analysis, European Journal of Operational Research, Volume 40, Issue 3, 15 June 1989, Pages 363–376 (http://www.sciencedirect.com/science/article/pii/0377221789904293). Bayesian Decision Analysis: Principles and Practice, Cambridge University Press, 2010 (https://books.google.com/books/about/Bayesian_Decision_Analysis.html?id=O1lXnQAACAAJ).

See also: Evaluating influence diagrams with decision circuits. In Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007)Operations Research, 34, 871-882

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.

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

Artificial intelligence, or AI, is largely an experimental science—at least as much progress has been made by building and analyzing programs as by examining theoretical questions. MYCIN is one of several well-known programs that embody some intelligence and provide data on the extent to which intelligent behavior can be programmed. As with other AI programs, its development was slow and not always in a forward direction. But we feel we learned some useful lessons in the course of nearly a decade of work on MYCIN and related programs. In this book we share the results of many experiments performed in that time, and we try to paint a coherent picture of the work. The book is intended to be a critical analysis of several pieces of related research, performed by a large number of scientists. We believe that the whole field of AI will benefit from such attempts to take a detailed retrospective look at experiments, for in this way the scientific foundations of the field will gradually be defined. It is for all these reasons that we have prepared this analysis of the MYCIN experiments.

The complete book in a single file.