Robert S. (Bob) Engelmore, who retired in 1998 He When the HPP's goal shifted to studying information Allan Terry's of Technology (later Carnegie Mellon University) Ph.D. dissertation and several publications and became a physics major. He had close grew out of this work. Working with crystallographers friendships with (later-to-be AI scientists) Professor Joseph Kraut and Dr. Steve Robert Lindsay and Ed Feigenbaum and Freer from the University of California at San roomed with Feigenbaum for six years of undergraduate Diego, Bob and Allan designed and implemented and graduate school. It graduate work, he met his future wife, Ellie, in was an ambitious project, involving sophisticated Pittsburgh. They were married in 1958.

I'm delighted to bring our readers the news of an exciting resource for AAAI members. AAAI has now completed a major initiative, begun five years ago, to develop a digital library of AAAI publications. The collection now comprises approximately 13,000 papers, including the full set of papers from the AAAI proceedings, papers from other major conferences, AAAI workshop and symposium technical reports, selected AAAI Press books, and the full contents of AI Magazine. This already-extensive collection is a growing resource, with new publications and access methods to be added over time. I encourage readers to visit it at the members' library section of the AAAI web site, www.aaai.org.

We hope by sending a message to majordomo@aaai.org AAAI regular members in the body of the message: subscribe can view and browse tables of aaai-members. Acapulco is the largest and most AAAI events and deadlines. They may also view, print, at www.aaai.org/AITopics/aitopics. stunning beaches, exuberant natural and/or download excerpts of reasonable html. Participation in this Registration information for the America, since its functional, modern experimental program is included in Eighteenth International Joint Conference infrastructure has had very little impact your normal AAAI membership dues.

Many of these systems were works The remainder of this article provides, in alphabetical in progress, providing the audience an opportunity order, brief discussions of each of to see snapshots of research programs in the entries based on text provided by their respective midphase. Contributors ranged from independent designers. The reader should assume undergraduate projects to large multilab that anything smart in the following pages is efforts. It there were nonetheless a number of recurring should also be mentioned that in the twentyfirst themes worth noting. Robotic systems for urban century, we not only have the problem of search and rescue (USAR), an area of growing what pronoun to use for individuals of unspecified interest for several years, have continued to gender (he, she, or they) but of what pronoun develop.

Raymond Reiter, a professor of computer science at the University of Toronto, a fellow of the Royal Society of Canada, and winner of the International Joint Conference on Artificial Intelligence 1993 Outstanding Research Scientist Award, died September 16, 2002, after a year-long struggle with cancer. Reiter, known throughout the world as "Ray," made foundational contributions to artifi- cial intelligence, knowledge representation and databases, and theorem proving.

This paper focuses on a system, WOLFIE (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with semantic representations. The lexicon learned consists of phrases paired with meaning representations. WOLFIE is part of an integrated system that learns to transform sentences into representations such as logical database queries. Experimental results are presented demonstrating WOLFIE's ability to learn useful lexicons for a database interface in four different natural languages. The usefulness of the lexicons learned by WOLFIE are compared to those acquired by a similar system, with results favorable to WOLFIE. A second set of experiments demonstrates WOLFIE's ability to scale to larger and more difficult, albeit artificially generated, corpora. In natural language acquisition, it is difficult to gather the annotated data needed for supervised learning; however, unannotated data is fairly plentiful. Active learning methods attempt to select for annotation and training only the most informative examples, and therefore are potentially very useful in natural language applications. However, most results to date for active learning have only considered standard classification tasks. To reduce annotation effort while maintaining accuracy, we apply active learning to semantic lexicons. We show that active learning can significantly reduce the number of annotated examples required to achieve a given level of performance.

Greedy approximation algorithms have been frequently used to obtain sparse solutions to learning problems. In this paper, we present a general greedy algorithm for solving a class of convex optimization problems. We derive a bound on the rate of approximation for this algorithm, and show that our algorithm includes a number of earlier studies as special cases.

We present a new approach to the supervised learning of lateral interactions for the competitive layer model (CLM) dynamic feature binding architecture. The method is based on consistency conditions, which were recently shown to characterize the attractor states of this linear threshold recurrent network. For a given set of training examples the learning problem is formulated as a convex quadratic optimization problem in the lateral interaction weights. An efficient dimension reduction of the learning problem can be achieved by using a linear superposition of basis interactions. We show the successful application of the method to a medical image segmentation problem of fluorescence microscope cell images.

We consider online learning in a Reproducing Kernel Hilbert Space. Our method is computationally efficient and leads to simple algorithms. In particular we derive update equations for classification, regression, and novelty detection. The inclusion of the -trick allows us to give a robust parameterization.

In this paper we introduce a new sparseness inducing prior which does not involve any (hyper)parameters that need to be adjusted or estimated. Although other applications are possible, we focus here on supervised learning problems: regression and classification. Experiments with several publicly available benchmark data sets show that the proposed approach yields state-of-the-art performance. In particular, our method outperforms support vector machines and performs competitively with the best alternative techniques, both in terms of error rates and sparseness, although it involves no tuning or adjusting of sparsenesscontrolling hyper-parameters.