Case-based reasoning provides both a methodology for building systems and a cognitive model of people. It is consistent with much that psychologists have observed in the natural problem solving people do. Psychologists have also observed, however, that people have several problems in doing analogical or case-based reasoning. Although they are good at using analogs to solve new problems, they are not always good at remembering the right ones. However, computers are good at remembering. I present case-based decision aiding as a methodology for building systems in which people and machines work together to solve problems. The case-based decision-aiding system augments the person's memory by providing cases (analogs) for a person to use in solving a problem. The person does the actual decision making using these cases as guidelines. I present an overview of case-based decision aiding, some technical details about how to implement such systems, and several examples of case-based systems.

The US Army has installed PRIDE Merlin is an expert system developed (Pulse Radar Intelligent Diagnostic at Hewlett Packard's Networked Environment), a diagnostic expert Computer Manufacturing Operation system developed by Carnegie Group (Roseville, CA) to forecast the factory's (Pittsburgh, PA), in Saudi Arabia in product demand. Lucid (Menlo Park, CA), producer of American Airlines (Dallas, TX) has the Lucid Common Lisp language, developed an expert system - Maintenance has acquired Peritus, a producer of Operation Control Advisor C/C and FORTRAN compilers. Consolidated Edison (New York, Nova Technology (Bethesda, MD), a NY) has developed the SOCCS Alarm new company founded by Naval Advisor, an expert system that recommends Research Center scientist Harold Szu, operator actions required plans to commercialize neural networks to maintain the necessary and continuous made from high-performance power supply to its customers. Kurzweil AI (Waltham, MA) has Inference (El Segundo, CA) has received a federal grant to develop named Peter Tierney CEO and president. VoiceGI, a voice-activated reporting Tierney was formerly VP of and database management system marketing at Oracle.

Thus, traditional (deterministic) planners can be useful in probabilistic domains.

Artificial Intelligence 51 (1991) 417-471, Spatial reasoning is ubiquitous in human problem solving. Significantly, many aspects of it appear to be qualitative. This paper describes a general framework for qualitative spatial reasoning and demonstrates how it can be used to understand complex mechanical systems, such as clocks. The framework is organized around three ideas.

In Lifschitz, V. (Ed.), Artificial Intelligence and Mathematical Theory of Computation: Papers in Honor of John McCarthy, pp. 359–380. Academic Press.

The growth in the amount of available databases far outstrips the growth of corresponding knowledge. This creates both a need and an opportunity for extracting knowledge from databases. Many recent results have been reported on extracting different kinds of knowledge from databases, including diagnostic rules, drug side effects, classes of stars, rules for expert systems, and rules for semantic query optimization.

In this paper we describe the VLSI design and testing of a high capacity associative memory which we call the exponential correlation 3J.'-CMOSassociative memory (ECAM). The prototype programmable chip is capable of storing 32 memory patterns of 24 bits each. The high capacity of the ECAM is partly due to the use of special exponentiation neurons, which are implemented via MOS transistors in this design. The prototype chipsub-threshold of performing one associative recall in 3 J.'S.is capable 1 ARCHITECTURE Previously (Chiueh, 1989), we have proposed a general model for correlation-based associative memories, which includes a variant of the Hopfield memory and highorder correlation memories as special cases. This new exponential correlation associative (ECAM) possesses a very large storage capacity, which scalesmemory exponentially with the length of memory patterns (Chiueh, 1988).

We have used information-theoretic ideas to derive a class of practical and nearly optimal schemes for adapting the size of a neural network. By removing unimportant weights from a network, several improvements can be expected: better generalization, fewer training examples required, and improved speed of learning and/or classification. The basic idea is to use second-derivative information to make a tradeoff between network complexity and training set error. Experiments confirm the usefulness of the methods on a real-world application. 1 INTRODUCTION Most successful applications of neural network learning to real-world problems have been achieved using highly structured networks of rather large size [for example (Waibel, 1989; Le Cun et al., 1990a)]. As applications become more complex, the networks will presumably become even larger and more structured.

We have done an empirical study of the relation of the number of parameters (weights) in a feedforward net to generalization performance.

Dataflow architectures are general computation engines optimized for the execution of fme-grain parallel algorithms. Neural networks can be simulated on these systems with certain advantages. In this paper, we review dataflow architectures, examine neural network simulation performance on a new generation dataflow machine, compare that performance to other simulation alternatives, and discuss the benefits and drawbacks of the dataflow approach.