David Rogers Research Institute for Advanced Computer Science MS 230-5, NASA Ames Research Center Moffett Field, CA 94035 ABSTRACT A new viewpoint of the processing performed by Kanerva's sparse distributed memory (SDM) is presented. In conditions of near-or over-capacity, where the associative-memory behavior of the model breaksdown, the processing performed by the model can be interpreted asthat of a statistical predictor. Mathematical results are presented which serve as the framework for a new statistical viewpoint ofsparse distributed memory and for which the standard formulation ofSDM is a special case. This viewpoint suggests possible enhancements to the SDM model, including a procedure for improving the predictiveness of the system based on Holland's work with'Genetic Algorithms', and a method for improving the capacity of SDM even when used as an associative memory. OVERVIEW This work is the result of studies involving two seemingly separate topics that proved to share a common framework. The fIrst topic, statistical prediction, is the task of associating extremely large perceptual state vectors with future events.

ABSTRACT The Parsing and Learning System(PALS) is a massively parallel self-tuning context-free parser. It is capable of parsing sentences of unbounded length mainly due to its parse-tree representation scheme. The system is capable of improving its parsing performance through the presentation of training examples. INTRODUCTION Recent PDP research[Rumelhart et al.- 1986; Feldman and Ballard, 1982; Lippmann, 1987] involving natural language processtng[Fanty, 1988; Selman, 1985; Waltz and Pollack, 1985] have unrealistically restricted sentences to a fixed length. A solution to this problem was presented in the system CONPARSE[Charniak and Santos.

This paper describes the construction of a system that recognizes hand-printed digits, using a combination of classical techniques and neural-net methods. The system has been trained and tested on real-world data, derived from zip codes seen on actual U.S. Mail. The system rejects a small percentage of the examples as unclassifiable, and achieves a very low error rate on the remaining examples. The system compares favorably with other state-of-the art recognizers. While some of the methods are specific to this task, it is hoped that many of the techniques will be applicable to a wide range of recognition tasks.

ALVINN (Autonomous Land Vehicle In a Neural Network) is a 3-layer back-propagation network designed for the task of road following. Currently ALVINNtakes images from a camera and a laser range finder as input and produces as output the direction the vehicle should travel in order to follow the road. Training has been conducted using simulated road images. Successful tests on the Carnegie Mellon autonomous navigation test vehicle indicate that the network can effectively follow real roads under certain field conditions. The representation developed to perfOIm the task differs dramatically whenthe networlc is trained under various conditions, suggesting the possibility of a novel adaptive autonomous navigation system capable of tailoring its processing to the conditions at hand.

We propose an optimality principle for training an unsupervised feedforwardneural network based upon maximal ability to reconstruct the input data from the network outputs. Wedescribe an algorithm which can be used to train either linear or nonlinear networks with certain types of nonlinearity. Examples of applications to the problems of image coding, feature detection, and analysis of randomdot stereogramsare presented.

Jim Saveland For a fire in that fuel complex to Research Forester The Phoenix project ("Trial by Fire: grow to the size indicated in the time Associate Editor, AI Application in Understanding the Design Requirements indicated would require a midflame Natural Resource Management for Agents in Complex Environments." Agriculture 3) presents very interesting work in The authors go on to state, "Firefighting Forest Service forest fire simulation. I am especially objects are also accurately Southern Forest Fire Laboratory glad to see recognition that the "realtime, simulated; for example, bulldozers Route 1, Box 182A spatially distributed, multiagent, move at a maximum speed of... 0.5 Dry Branch, GA 31020 dynamic, and unpredictable fire kph when cutting a fireline." In reality, environment" provides an excellent sustained fireline production for Editor: opportunity to explore a variety of AI bulldozers is variable (0.1 - 2.0 kph) issues, such as how complex environments depending on steepness of the slope, Mr. Saveland's letter focuses our constrain the design of intelligent vegetation, and size of the bulldozer. I hope more AI researchers Furthermore, although bulldozers are between accuracy and realism.

Giving Is Hard: The Complexity of Linear Navigation and Xiaofeng Chen, Wright State University, 274 SC9j22, Santa Clara, CA 95052.

A panel session at the 1989 International Joint Conference on Artificial Intelligence in Los Angeles dealt with the subject of knowledge-based systems; the session was entitled "Expert Systems: How Far Can They Go?" The panelists included Randall Davis (Massachusetts Institute of Technology); Stuart Dreyfus (University of California at Berkeley); Brian Smith (Xerox Palo Alto Research Center); and Terry Winograd (Stanford University), chairman. Part 1 of this article, which appeared in the Spring 1989 issue, began with Winograd's original charge to the panel, followed by lightly edited transcripts of presentations from Winograd and Dreyfus. Part 2 begins with the presentations from Smith and Davis and concludes with the panel discussion. Although almost four years have passed since this discussion took place, the issues raised and the points discussed appear no less relevant today.

Commentators on AI converge on two goals they believe define the field: (1) to better understand the mind by specifying computational models and (2) to construct computer systems that perform actions traditionally regarded as mental. We should recognize that AI has a third, hidden, more basic aim; that the first two goals are special cases of the third; and that the actual technical substance of AI concerns only this more basic aim. This third aim is to establish new computation-based representational media, media in which human intellect can come to express itself with different clarity and force. This article articulates this proposal by showing how the intellectual activity we label AI can be likened in revealing ways to each of five familiar technologies.

Artificial Intelligence is solving more and more real world problems, but penetration into the complexities of government administration has been minimal. The author suggests that combining expert system technology with conventional procedural computer systems can lead to substantial efficiencies. Business rules can be removed from business-oriented computer systems and stored in a separate but integrated knowledge base, where maintenance will be centralized. Fourteen specific practical applications are suggested.