He knew the challenges opinion, as one of the premier natural language were great and would require the research groups in the world. He gave efforts of many people. He had a genius for one of us (Barbara Grosz) her first AI job, even bringing these people together. In doing so, he took a of people who had known Don over the risk of a magnitude that she fully appreciated years to send us reminiscences. Although only years later when she herself was hiring each person's story differed, a striking commonality research associates.

Dartnall, Terry, see Kim, Steven Davis, Randall; Shrobe, Howard; and Szolovits, Peter. What Is a Knowledge 1992 AAAI Robot Exhibition and Competition Leonard, Lisa. Dean, Thomas; and Bonasso, R. Capture and Use, The, see Lee, Jintae Technologies, see Barachini, Franz Cannel Versus Flakey: A Comparison of Dean, Tom, see Joskowicz, Leo. Reasoning Dorr, Bonnie J. Building Lexicons for see Tanner, Steve with Diagrammatic Representations: A Machine Translation: 1993 Spring Anick, Peter; and Simoudis, Evange-Report on the Spring Symposium. Retrieval: 1993 Spring Symposium Charniak, Eugene, see Goldman, Drummond, Mark, see Lansky, Amy Report.

The competition, rules, coordinating the setup and Technologies, showed off a unique which attracted teams from administration of the contest, and global-positioning system using a many of the top mobile robotics trying to cope with the needs of the robot-mounted revolving laser and research laboratories in the United 15 teams that put so much energy three or more stationary receivers. States (see side bar), was first proposed into their entries. This article reports Still, many teams suffered frustrating by Thomas Dean and held at some of the experiences I had in failures in hardware and especially the 1992 NCAI conference. Dean's helping to design and run the contest software, leading to a general lack concept was to further the research and some reflections, drawn of sleep and noticeable exhaustion into the skills such robots from post mortem abstracts written among the contestants by Monday need--sensing, interpretation, planning, by the competitors, on the relation of night, the day before the contest. I and reacting--by bringing the contest to current research efforts know this from personal experience: together interested parties in a cooperative in mobile robotics.

We report on a series of experiments in which all decision trees consistent with the training data are constructed. These experiments were run to gain an understanding of the properties of the set of consistent decision trees and the factors that affect the accuracy of individual trees. In particular, we investigated the relationship between the size of a decision tree consistent with some training data and the accuracy of the tree on test data. The experiments were performed on a massively parallel Maspar computer. The results of the experiments on several artificial and two real world problems indicate that, for many of the problems investigated, smaller consistent decision trees are on average less accurate than the average accuracy of slightly larger trees.

This book (originally published in 1994 by Ellis Horwood) is now out of print. The copyright now resides with the editors who have decided to make the material freely available on the web.This book is based on the EC (ESPRIT) project StatLog which compare and evaluated a range of classification techniques, with an assessment of their merits, disadvantages and range of application. This integrated volume provides a concise introduction to each method, and reviews comparative trials in large-scale commercial and industrial problems. It makes accessible to a wide range of workers the complex issue of classification as approached through machine learning, statistics and neural networks, encouraging a cross-fertilization between these discplines.

Learning the past tense of English verbs - a seemingly minor aspect of language acquisition - has generated heated debates since 1986, and has become a landmark task for testing the adequacy of cognitive modeling. Several artificial neural networks (ANNs) have been implemented, and a challenge for better symbolic models has been posed. In this paper, we present a general-purpose Symbolic Pattern Associator (SPA) based upon the decision-tree learning algorithm ID3. We conduct extensive head-to-head comparisons on the generalization ability between ANN models and the SPA under different representations. We conclude that the SPA generalizes the past tense of unseen verbs better than ANN models by a wide margin, and we offer insights as to why this should be the case. We also discuss a new default strategy for decision-tree learning algorithms.

The ability to identify interesting and repetitive substructures is an essential component to discovering knowledge in structural data. We describe a new version of our SUBDUE substructure discovery system based on the minimum description length principle. The SUBDUE system discovers substructures that compress the original data and represent structural concepts in the data. By replacing previously-discovered substructures in the data, multiple passes of SUBDUE produce a hierarchical description of the structural regularities in the data. SUBDUE uses a computationally-bounded inexact graph match that identifies similar, but not identical, instances of a substructure and finds an approximate measure of closeness of two substructures when under computational constraints. In addition to the minimum description length principle, other background knowledge can be used by SUBDUE to guide the search towards more appropriate substructures. Experiments in a variety of domains demonstrate SUBDUE's ability to find substructures capable of compressing the original data and to discover structural concepts important to the domain. Description of Online Appendix: This is a compressed tar file containing the SUBDUE discovery system, written in C. The program accepts as input databases represented in graph form, and will output discovered substructures with their corresponding value.

The theory revision problem is the problem of how best to go about revising a deficient domain theory using information contained in examples that expose inaccuracies. In this paper we present our approach to the theory revision problem for propositional domain theories. The approach described here, called PTR, uses probabilities associated with domain theory elements to numerically track the ``flow'' of proof through the theory. This allows us to measure the precise role of a clause or literal in allowing or preventing a (desired or undesired) derivation for a given example. This information is used to efficiently locate and repair flawed elements of the theory. PTR is proved to converge to a theory which correctly classifies all examples, and shown experimentally to be fast and accurate even for deep theories.

Phil. Trans. R. Soc. Lond. A. 1994 349 1689. Intelligence is a complex, natural phenomenon exhibited by humans and many other living things, without sharply defined boundaries between intelligent and unintelligent behaviour. Artificial inteliigence focuses on the phenomenon of intelligent behaviour, in humans or machines. Experimentation with computer programs allows us to manipulate their design and intervene in the environmental conditions in ways that are not possible with humans. Thus, experimentation can help us to understand what principles govern intelligent action and what mechanisms are sufficient for computers to replicate intelligent behaviours.

A formalism is presented for computing and organizing actions for autonomous agents in dynamic environments. We introduce the notion of teleo-reactive (T-R) programs whose execution entails the construction of circuitry for the continuous computation of the parameters and conditions on which agent action is based. In addition to continuous feedback, T-R programs support parameter binding and recursion. A primary difference between T-R programs and many other circuit-based systems is that the circuitry of T-R programs is more compact; it is constructed at run time and thus does not have to anticipate all the contingencies that might arise over all possible runs. In addition, T-R programs are intuitive and easy to write and are written in a form that is compatible with automatic planning and learning methods. We briefly describe some experimental applications of T-R programs in the control of simulated and actual mobile robots.