Artificial Intelligence Series – serie

This book is the third volume in a series that provides a hands-on perspective on the evolving theories associated with Roger Schank and his students. The primary focus of this volume is on constructing explanations. All of the chapters relate to the problem of building computer programs that can develop hypotheses about what might have caused an observed event. Because most researchers in natural language processing don't really want to work on inference, memory, and learning issues, most of their sample text fragments are chosen carefully to de-emphasize the need for non text-related reasoning. The ability to come up with hypotheses about what is really going on in a story is a hallmark of human intelligence. The biggest difference between truly intelligent readers and less intelligent ones is the extent to which the reader can go beyond merely understanding the explicit statements being communicated. Achieving a creative level of understanding means developing hypotheses about questions for which there may be no conclusively correct answer at all. The focus of the lab, during the period documented in this book, was to work on getting a computer program to do that. The volume adopts a case-based approach to the construction of explanations which suggests that the main steps in the process of explaining a given anomaly are as follows: * Retrieve an explanation that might be relevant to the anomaly. * Evaluate whether the retrieved explanation makes sense when applied to the current anomaly. * Adapt the explanation to produce a new variant that fits better if the retrieved explanation doesn't fit the anomaly perfectly.

This book is the third volume in a series that provides a hands-on perspective on the evolving theories associated with Roger Schank and his students. The primary focus of this volume is on constructing explanations. All of the chapters relate to the problem of building computer programs that can develop hypotheses about what might have caused an observed event. Because most researchers in natural language processing don't really want to work on inference, memory, and learning issues, most of their sample text fragments are chosen carefully to de-emphasize the need for non text-related reasoning. The ability to come up with hypotheses about what is really going on in a story is a hallmark of human intelligence. The biggest difference between truly intelligent readers and less intelligent ones is the extent to which the reader can go beyond merely understanding the explicit statements being communicated. Achieving a creative level of understanding means developing hypotheses about questions for which there may be no conclusively correct answer at all. The focus of the lab, during the period documented in this book, was to work on getting a computer program to do that. The volume adopts a case-based approach to the construction of explanations which suggests that the main steps in the process of explaining a given anomaly are as follows: * Retrieve an explanation that might be relevant to the anomaly. * Evaluate whether the retrieved explanation makes sense when applied to the current anomaly. * Adapt the explanation to produce a new variant that fits better if the retrieved explanation doesn't fit the anomaly perfectly.

Summarizes and illuminates two decades of researchGathering important papers by both philosophers and scientists, this collection illuminates the central themes that have arisen during the last two decades of work on the conceptual foundations of artificial intelligence and cognitive science. Each volume begins with a comprehensive introduction that places the coverage in a broader perspective and links it with material in the companion volumes. The collection is of interest in many disciplines including computer science, linguistics, biology, information science, psychology, neuroscience, iconography, and philosophy.Examines initial efforts and the latest controversiesThe topics covered range from the bedrock assumptions of the computational approach to understanding the mind, to the more recent debates concerning cognitive architectures, all the way to the latest developments in robotics, artificial life, and dynamical systems theory. The collection first examines the lineage of major research programs, beginning with the basic idea of machine intelligence itself, then focuses on specific aspects of thought and intelligence, highlighting the much-discussed issue of consciousness, the equally important, but less densely researched issue of emotional response, and the more traditionally philosophical topic of language and meaning.Provides a gamut of perspectivesThe editors have included several articles that challenge crucial elements of the familiar research program of cognitive science, as well as important writings whose previous circulation has been limited. Within each volume the papers are organized to reflect a variety of research programs and issues. The substantive introductions that accompany each volume further organize the material and provide readers with a working sense of the issues and the connection between articles.

First published in 1981. This book has been written for those who want to comprehend how a large natural language-understanding program works. Thirty-five professionals in Cognitive Science, mostly psychologists by training, in a summer school were taught to grapple with the details of programming in Artificial Intelligence. As a part of the curriculum designed for this project the authors created what they called micro-programs. These micro-programs were an attempt to give students the flavor of using a large AI program without all the difficulty normally associated with learning a complex system written by another person. Using the authors’ parser, ELI, or story understanding program, SAM, they also gave students the micro versions of these programs, which were very simple versions that operated in roughly the same way as their larger versions, but without all the frills. Students were asked to add pieces to the programs and otherwise modify them in order to learn how they worked.

First Published in 1977. In the summer of 1971, there was a workshop in an ill-defined field at the intersection of psychology, artificial intelligence, and linguistics. The fifteen participants were in various ways interested in the representation of large systems of knowledge (or beliefs) based upon an understanding process operating upon information expressed in natural language. This book reflects a convergence of interests at the intersection of psychology and artificial intelligence. What is the nature of knowledge and how is this knowledge used? These questions lie at the core of both psychology and artificial intelligence.

First published in 1986. The chapters in this collection are based on presentations made at the First Annual Workshop on Theoretical Issues in Conceptual Information Processing (TICIP) grew out of that. It was held in Atlanta, Georgia in March 1984 and included 50 people with roughly the same world view. In particular, the contributors were interested in content-based theories of conceptual information processing. Each chapter addresses some issue associated with the relationships between memory, experience and reasoning.

Introducing issues in dynamic memory and case-based reasoning, this comprehensive volume presents extended descriptions of four major programming efforts conducted at Yale during the past several years. Each descriptive chapter is followed by a companion chapter containing the micro program version of the information. The authors emphasize that the only true way to learn and understand any AI program is to program it yourself. To this end, the book develops a deeper and richer understanding of the content through LISP programming instructions that allow the running, modification, and extension of the micro programs developed by the authors.

A recent area of interest in the Artificial Intelligence community has been the application of massively parallel algorithms to enhance the choice mechanism in traditional AI problems. This volume provides a detailed description of how marker-passing -- a parallel, non-deductive, spreading activation algorithm -- is a powerful approach to refining the choice mechanisms in an AI problem-solving system. The author scrutinizes the design of both the algorithm and the system, and then reviews the current literature and research in planning and marker passing. Also included: a comparison of this computer model with some standard cognitive models, and a comparison of this model to the "connectionist" approach.

Psychology and philosophy have long studied the nature and role of explanation. More recently, artificial intelligence research has developed promising theories of how explanation facilitates learning and generalization. By using explanations to guide learning, explanation-based methods allow reliable learning of new concepts in complex situations, often from observing a single example. The author of this volume, however, argues that explanation-based learning research has neglected key issues in explanation construction and evaluation. By examining the issues in the context of a story understanding system that explains novel events in news stories, the author shows that the standard assumptions do not apply to complex real-world domains. An alternative theory is presented, one that demonstrates that context -- involving both explainer beliefs and goals -- is crucial in deciding an explanation's goodness and that a theory of the possible contexts can be used to determine which explanations are appropriate. This important view is demonstrated with examples of the performance of ACCEPTER, a computer system for story understanding, anomaly detection, and explanation evaluation.