Doug Fisher

Hans-J. Lenz

Hans-J Lenz

This volume contains a revised collection of papers originally presented at the Fifth International Workshop on Artificial Intelligence and Statistics in 1995. The topics represented in this volume are diverse, and include natural language application causality and graphical models, classification, learning, knowledge discovery, and exploratory data analysis. The chapters illustrate the rich possibilities for interdisciplinary study at the interface of artificial intelligence and statistics. The chapters vary in the background that they assume, but moderate familiarity with techniques of artificial intelligence and statistics is desirable in most cases.

Artificial Intelligence and Statistics V

Learning from Data

Rudolf Kruse

Didier Dubois

Giacomo Della Riccia

Planning of actions based on decision theory is a hot topic for many disciplines. Seemingly unlimited computing power, networking, integration and collaboration have meanwhile attracted the attention of fields like Machine Learning, Operations Research, Management Science and Computer Science. Software agents of e-commerce, mediators of Information Retrieval Systems and Database based Information Systems are typical new application areas. Until now, planning methods were successfully applied in production, logistics, marketing, finance, management, and used in robots, software agents etc. It is the special feature of the book that planning is embedded into decision theory, and this will give the interested reader new perspectives to follow-up.

Planning Based on Decision Theory

Ten years ago Bill Gale of AT&T Bell Laboratories was primary organizer of the first Workshop on Artificial Intelligence and Statistics. In the early days of the Workshop series it seemed clear that researchers in AI and statistics had common interests, though with different emphases, goals, and vocabularies. In learning and model selection, for example, a historical goal of AI to build autonomous agents probably contributed to a focus on parameter-free learning systems, which relied little on an external analyst's assumptions about the data. This seemed at odds with statistical strategy, which stemmed from a view that model selection methods were tools to augment, not replace, the abilities of a human analyst. Thus, statisticians have traditionally spent considerably more time exploiting prior information of the environment to model data and exploratory data analysis methods tailored to their assumptions. In statistics, special emphasis is placed on model checking, making extensive use of residual analysis, because all models are 'wrong', but some are better than others. It is increasingly recognized that AI researchers and/or AI programs can exploit the same kind of statistical strategies to good effect. Often AI researchers and statisticians emphasized different aspects of what in retrospect we might now regard as the same overriding tasks.

Hans-J. Lenz

About

Books

Join the club