Based on the experience in manufacturing production scheduling problems which the AI community has amassed over the last ten years, a workshop was held to provide a forum for discussion of the issues encountered in the design of AI-based scheduling systems. Several topics were addressed including : the relative virtues of expert system, deep method, and interactive approaches, the balance between predictive and reactive components in a scheduling system, the maintenance of convenient scheduling descriptions, the application of the ideas of chaos theory to scheduling, the state of the art in schedulers which learn, and the practicality and desirability of a set of benchmark scheduling problems. This article expands on these issues, abstracts the papers which were presented, and summarizes the lengthy discussions that took place.

This symposium was very successful and was perhaps the most unusual of the spring symposia this year. It brought together for the first time distinguished researchers from many diverse disciplines to discuss and share results on a particular topic of mutual interest. The disciplines included machine learning, computational learning theory, computer vision, pattern recognition, perceptual psychology, statistics, information theory, theoretical computer science, and molecular biology, with the involvement of the latter group having lead to a joint session with the AI and Molecular Biology symposium.

Truth maintenance is a collection of techniques for doing belief revision. A truth maintenance system's task is to maintain a set of beliefs in such a way that they are not known to be contradictory and no belief is kept without a reason. Truth maintenance systems were introduced in the late seventies by Jon Doyle and in the last five years there has been an explosion of interest in this kind of systems. In this paper we present an annotated bibliography to the literature of truth maintenance systems, grouping the works referenced according to several classifications.

Clancey troubleshooting tutor for only 20 The cognitive modeling group provided would like to see alternative cognitive hours gained a proficiency equivalent strong advocacy for the use of models available within a system to that of trainees with 40 months cognitive modeling in building these rather than a single "correct" model (almost 4 years) on-the-job training systems. They argued for increased used to justify instruction.

There is a great disparity between the number of papers which have been published about AI-based manufacturing scheduling tools and the number of systems which are in daily use by manufacturing engineers. It is argued that this is not a reflection of inadequate AI technology, but is rather indicative of lack of a systems perspective by AI practitioners and their manufacturing customers. Case studies to support this perspective are presented by Carnegie Group as a builder of scheduling systems for its customers, by Texas Instruments and Intel Corporation as builders of schedulers for their own use, and by Intellection as a consulting house specializing in scheduling problems.

In this paper we compare regression and classification systems. A regression system can generate an output f for an input X, where both X and f are continuous and, perhaps, multidimensional. A classification system can generate an output class, C, for an input X, where X is continuous and multidimensional and C is a member of a finite alphabet. The statistical technique of Classification And Regression Trees (CART) was developed during the years 1973 (Meisel and Michalpoulos) through 1984 (Breiman el al).

It is generally admitted that generalization performance of back-propagation networks (Rumelhart,Hinton & Williams, 1986) will depend on the relative size ofthe training data and of the trained network. By analogy to curve-fitting and for theoretical considerations,the generalization performance of the network should decrease as the size of the network and the associated number of degrees of freedom increase (Rumelhart, 1987; Denker et al., 1987; Hanson & Pratt, 1989). This paper examines the dynamics of the standard back-propagation algorithm (BP) and of a constrained back-propagation variation (CBP), designed to adapt the size of the network to the training data base. The performance, learning dynamics and the representations resulting from the two algorithms are compared.

We are developing a phoneme based.

We present a model of catecholamine effects in a network of neural-like elements. We argue that changes in the responsivity of individual elements do not affect their ability to detect a signal and ignore noise. However. the same changes in cell responsivity in a network of such elements do improve the signal detection performance of the network as a whole. We show how this result can be used in a computer simulation of behavior to account for the effect of eNS stimulants on the signal detection performance of human subjects.

A new learning algorithm, Learning by Choice of Internal Represetations (CHIR),was recently introduced. Whereas many algorithms reduce the learning process to minimizing a cost function over the weights, our method treats the internal representations as the fundamental entities to be determined. The algorithm applies a search procedure in the space of internal representations, and a cooperative adaptation of the weights (e.g. by using the perceptron learning rule). Since the introduction of its basic, single output version, theCHIR algorithm was generalized to train any feed forward network of binary neurons. Here we present the generalised version of the CHIR algorithm, and further demonstrate its versatility by describing how it can be modified in order to train networks with binary ( 1) weights. Preliminary tests of this binary version on the random teacher problem are also reported.