Current Focus Of Learning Research Most connectionist learning algorithms may be grouped into three general catagories, commonly referred to as supenJised, unsupenJised, and reinforcement learning. Supervised learning requires the explicit participation of an intelligent teacher, usually to provide the learning system with task-relevant input-output pairs (for two recent examples, see [1,2]). Unsupervised learning, exemplified by "clustering" algorithms, are generally concerned with detecting structure in a stream of input patterns [3,4,5,6,7]. In its final state, an unsupervised learning system will typically represent the discovered structure as a set of categories representing regions of the input space, or, more generally, as a mapping from the input space into a space of lower dimension that is somehow better suited to the task at hand. In reinforcement learning, a "critic" rewards or penalizes the learning system, until the system ultimately produces the correct output in response to a given input pattern [8]. It has seemed an inevitable tradeoff that systems needing to rapidly learn specific, behaviorally useful input-output mappings must necessarily do so under the auspices of an intelligent teacher with a ready supply of task-relevant training examples. This state of affairs has seemed somewhat paradoxical, since the processes of Rerceptual and cognitive development in human infants, for example, do not depend on the moment by moment intervention of a teacher of any sort. Learning by Doing The current work has been focused on a fourth type of learning algorithm, i.e. learning-bydoing, an approach that has been very little studied from either a connectionist perspective

To demonstrate these methods we have trained an ANS network to drive a vehicle through simulated rreeway traffic. I ntJooducticn Computational systems employing fine grained parallelism are revolutionizing the way we approach a number or long standing problems involving pattern recognition and cognitive processing. Thefield spans a wide variety or computational networks, rrom constructs emulating neural runctions, to more crystalline configurations that resemble systolic arrays. Several titles are used to describe this broad area or research, we use the term artificial neural systems (ANS). Our concern inthis work is the use or ANS ror manually training certain types or autonomous systems where the desired rules of behavior are difficult to rormulate. Artificial neural systems consist of a number or processing elements interconnected in a weighted, user-specified fashion, the interconnection weights acting as memory ror the system. Each processing element calculatE', an output value based on the weighted sum or its inputs. In addition, the input data is correlated with the output or desired output (specified by an instructive agent) in a training rule that is used to adjust the interconnection weights.

WINTER 1988 79 Notes to Financial Statements Program Committee (reported by Reid accounting principles applied on a Smith, Program Co-Chair).

A workshop on high-level connectionist models was held in Las Cruces, New Mexico, on 9-11 April 1988 with support from the Association for the Advancement of Artificial Intelligence and the Office of Naval Research. John Barnden and Jordan Pollack organized and hosted the workshop and will edit a book containing the proceedings and commentary. The book will be published by Ablex as the first volume in a series entitled Advances in Connectionist and Neural Computation Theory.

James Peters, coauthor of "A Knowledge-Based Model of Audit Risk," is an assistant professor in the Department of Accounting, College of Business Administration, University of Oregon. Glenn D. Rennels coauthor of "Prose Generation from Expert Systems: An Applied Computational Linguistics Thomas Arcidiacono, the author of the review of An Artificial Intelligence Approach, " is a research affiliate in Approach to Legal Reasoning, is affiliated with the Artificial Intelligence Laboratory, the Medical Information Sciences Program, the New York Institute of Technology, Sunburst Center 203, Central Edwina L. Rissland, author of "Artificial Intelligence and Legal Reasoning: R. Peter Bonasso, author of "An Hermann Kaindl, author of "Minimaxing: A Discussion of the Field and Assessment of What AI Can Do for Theory and Practice", is a Gardner's Book," is an associate professor Battle Management--A Report of the software engineer in the position of of Computer and Information First AAAI Workshop on AI Applications "Gruppenleiter" at Siemens AG Science at the University of Massachusetts to Battle Management" is the osterreich, Program and System Engineering at Amherst and lecturer on department head of the Artificial Since 1984, he has been a lecturer law at the Harvard Law School. Operations division, 7525 Colshire research interests include planning Drive, Mclean, VA 22102. Vasant Dhar, coauthor of "A Knowledge-Based Model of Audit Risk," is Model of Audit Risk," is Peat Marwick Professor of Accounting, Kenneth D. Forbus is an assistant professor Perry Miller, coauthor of "Prose Generation of computer science at the University from Expert Systems: An Call toU-free 800-521-3044 Or mail inquiry to: University Microfilms International. Forbus's research interests Program, Yale University include qualitative reasoning, inference School of Medicine, 333 Cedar Street, engine design, analogical reasoning P.O.

The goal of intelligent computer-aided engineering (ICAE) is to construct computer programs that capture a significant fraction of an engineer's knowledge. Today, ICAE systems are a goal, not a reality. This article attempts to refine that goal and suggest how to get there. We begin by examining several scenarios of what ICAE systems could be like. Next we describe why ICAE won't evolve directly from current applications of expert system technology to engineering problems. I focus on qualitative physics as a critical area where progress is needed, both in terms of representations and styles of reasoning.

It was felt that the AIM Szolovits responding, and "Uncertainty approaches, augmenting explanations

The Computing Research Laboratory (CRL) at New Mexico State University is a center for research in artificial intelligence and cognitive science. Specific areas of research include the human-computer interface, natural language understanding, connectionism, knowledge representation and reasoning, computer vision, robotics, and graph theory. This article describes the ongoing projects at CRL.

A qualitative physics which captures the depth and breadth of an engineer's knowledge will be orders of magnitude larger than the models of today's qualitative physics. To build and use such models effectively requires explicit modeIing assumptions to manage complexity. This, in turn, gives rise to the problem of selecting the right qualitative model for some purpose.

Wiley is a global provider of content and content-enabled workflow solutions in areas of scientific, technical, medical, and scholarly research; professional development; and education. Our core businesses produce scientific, technical, medical, and scholarly journals, reference works, books, database services, and advertising; professional books, subscription products, certification and training services and online applications; and education content and services including integrated online teaching and learning resources for undergraduate and graduate students and lifelong learners. Founded in 1807, John Wiley & Sons, Inc. has been a valued source of information and understanding for more than 200 years, helping people around the world meet their needs and fulfill their aspirations. Wiley has published the works of more than 450 Nobel laureates in all categories: Literature, Economics, Physiology or Medicine, Physics, Chemistry, and Peace. Wiley has partnerships with many of the world's leading societies and publishes over 1,500 peer-reviewed journals and 1,500 new books annually in print and online, as well as databases, major reference works and laboratory protocols in STMS subjects.