Paul Cohen's book Empirical Methods for Artificial Intelligence aims to encourage this trend by providing AI practitioners with the knowledge and tools needed for careful empirical evaluation. The volume provides broad coverage of experimental design and statistics, ranging from a gentle introduction of basic ideas to a detailed presentation of advanced techniques, often combined with illustrative examples of their application to the empirical study of AI. The book is generally well written, clearly organized, and easy to understand; it contains some mathematics -- but not enough to overwhelm readers. Examples come from AI work on planning, machine learning, natural language, and diagnosis.

Data mining and knowledge discovery in databases have been attracting a significant amount of research, industry, and media attention of late. What is all the excitement about? This article provides an overview of this emerging field, clarifying how data mining and knowledge discovery in databases are related both to each other and to related fields, such as machine learning, statistics, and databases. The article mentions particular real-world applications, specific data-mining techniques, challenges involved in real-world applications of knowledge discovery, and current and future research directions in the field.

Anytime algorithms give intelligent systems the capability to trade deliberation time for quality of results. This capability is essential for successful operation in domains such as signal interpretation, real-time diagnosis and repair, and mobile robot control. What characterizes these domains is that it is not feasible (computationally) or desirable (economically) to compute the optimal answer. This article surveys the main control problems that arise when a system is composed of several anytime algorithms. These problems relate to optimal management of uncertainty and precision. After a brief introduction to anytime computation, I outline a wide range of existing solutions to the metalevel control problem and describe current work that is aimed at increasing the applicability of anytime computation.

The Association for the Advancement of Artificial Intelligence held its 1996 Spring Symposia Series on March 27 to 29 at Stanford University. This article contains summaries of the eight symposia that were conducted: (1) Acquisition, Learning, and Demonstration: Automating Tasks for Users; (2) Adaptation, Coevolution, and Learning in Multiagent Systems; (3) Artificial Intelligence in Medicine: Applications of Current Technologies; (4) Cognitive and Computational Models of Spatial Representation; (5) Computational Implicature: Computational Approaches to Interpreting and Generating Conversational Implicature; (6) Computational Issues in Learning Models of Dynamic Systems; (7) Machine Learning in Information Access; and (8) Planning with Incomplete Information for Robot Problems.

A significant and growing area of business-computing research is concerned with AI. Knowledge about which journals are the most influential forums for disseminating AI research is important for business school faculty, students, administrators, and librarians. To date, there has been only one study attempting to rank AI journals from a business-computing perspective. It used a subjective methodology, surveying opinions of business faculty about a prespecified list of 30 journals. Here, we report the results of a more objective study. We conducted a citation analysis covering a time period of 5 years to compile 15,600 citations to 1,244 different journals. Based on these data, the journals are ranked in two ways involving the magnitude and the duration of scientific impact each has had in the field of AI.

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

For many types of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992; Cohn, 1994]. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Many different discrete-time recurrent neural network architectures have been proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.

For many types of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992; Cohn, 1994]. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Many different discrete-time recurrent neural network architectures have been proposed. However, there has been virtually no effort to compare these arch:tectures experimentally. In this paper we review and categorize many of these architectures and compare how they perform on various classes of simple problems including grammatical inference and nonlinear system identification.