Concept Formation: Knowledge and Experience in Unsupervised Learning presents the interdisciplinary interaction between machine learning and cognitive psychology on unsupervised incremental methods. This book focuses on measures of similarity, strategies for robust incremental learning, and the psychological consistency of various approaches. Organized into three parts encompassing 15 chapters, this book begins with an overview of inductive concept learning in machine learning and psychology, with emphasis on issues that distinguish concept formation from more prevalent supervised methods and from numeric and conceptual clustering. This text then describes the cognitive consistency of two concept formation systems that are motivated by a rational analysis of human behavior relative to a variety of psychological phenomena. Other chapters consider the merits of various schemes for representing and acquiring knowledge during concept formation. This book discusses as well the earliest work in concept formation. The final chapter deals with acquisition of quantity conservation in developmental psychology. This book is a valuable resource for psychologists and cognitive scientists.

This book treats memory and understanding on two levels, on the phenomenological level of experience, on which a theory of dynamic conceptual semantics is built, and on the neuro-connectionist level, which supports the capacities of concept formation, remembering, and understanding. A neuro-connectionist circuit architecture of a constructive memory is developed in which understanding and remembering are modelled in accordance with the constituent structures of a dynamic conceptual semantics. Consciousness emerges by circuit activation between conceptual indicators and episodic indices with the sensory-motor, emotional, and proprioceptual areas. This theory of concept formation, remembering, and understanding is applied to Proust s "A la recherche du temps perdu," with special attention to the author s excursions into philosophical and aesthetic issues. Under this perspective, Proust s work can be seen as an artistic exploration into our capacity of understanding, whereby the unconscious, the memory, is exteriorized in consciousness by presenting the experienced episodes in the conceptual order of similarity and contiguity through our capacity of concept formation. (Series A)

Concepts embody our knowledge of the kinds of things there are in the world. Tying our past experiences to our present interactions with the environment, they enable us to recognize and understand new objects and events. Concepts are also relevant to understanding domains such as social situations, personality types, and even artistic styles. Yet like other phenomenologically simple cognitive processes such as walking or understanding speech, concept formation and use are maddeningly complex. Research since the 1970s and the decline of the "classical view" of concepts have greatly illuminated the psychology of concepts. But persistent theoretical disputes have sometimes obscured this progress. The Big Book of Concepts goes beyond those disputes to reveal the advances that have been made, focusing on the major empirical discoveries. By reviewing and evaluating research on diverse topics such as category learning, word meaning, conceptual development in infants and children, and the basic level of categorization, the book develops a much broader range of criteria than is usual for evaluating theories of concepts.

A fundamental assumption of work in artificial intelligence and machine learning is that knowledge is expressed in a computer with the help of knowledge representations. Since the proper choice of such representations is a difficult task that fundamentally affects the capabilities of a system, the problem of automatic representation change is an important topic in current research. Concept Formation and Knowledge Revision focuses on representation change as a concept formation task, regarding concepts as the elementary representational vocabulary from which further statements are constructed. Taking an interdisciplinary approach from psychological foundations to computer implementations, the book draws on existing psychological results about the nature of human concepts and concept formation to determine the scope of concept formation phenomena, and to identify potential components of computational concept formation models. The central idea of this work is that computational concept formation can usefully be understood as a process that is triggered in a demand-driven fashion by the representational needs of the learning system, and identify the knowledge revision activities of a system as a particular context for such a process. The book presents a detailed analysis of the revision problem for first-order clausal theories, and develops a set of postulates that any such operation should satisfy. It shows how a minimum theory revision operator can be realized by using exception sets, and that this operator is indeed maximally general. The book then shows that concept formation can be triggered from within the knowledge revision process whenever the existing representation does not permit the plausible reformulation of an exception set, demonstrating the usefulness of the approach both theoretically and empirically within the learning knowledge acquisition system MOBAL. In using a first-order representation, this book is part of the rapidly developing field of Inductive Logic Programming (ILP). By integrating the computational issues with psychological and fundamental discussions of concept formation phenomena, the book will be of interest to readers both theoretically and psychologically inclined. From the foreword by Katharina Morik: ` The ideal to combine the three sources of artificial intelligence research has almost never been reached. Such a combined and integrated research requires the researcher to master different ways of thinking, different work styles, different sets of literature, and different research procedures. It requires capabilities in software engineering for the application part, in theoretical computer science for the theory part, and in psychology for the cognitive part. The most important capability for artificial intelligence is to keep the integrative view and to create a true original work that goes beyond the collection of pieces from different fields. This book achieves such an integrative view of concept formation and knowledge revision by presenting the way from psychological investigations that indicate that concepts are theories and point at the important role of a demand for learning. to an implemented system which supports users in their tasks when working with a knowledge base and its theoretical foundation. '

First published in 1983, this book examines the problems of concept formation in the social sciences, and in particular sociology, from the standpoint of a realistic philosophy of science. Beginning with a discussion of positivistic, hermeneutic, rationalist and realistic philosophies of science, Dr Outhwaite argues that realism is best able to furnish rational criteria for the choice and specification of social scientific concepts. A realistic philosophy of science therefore acts as his reference point for the dialectical presentation of alternative accounts.

Volume eight in this highly acclaimed series discusses the behavioral approaches to pattern recognition and concept formation in two sections: categories and concepts in birds, and shape and form. An ideal reference for students and professionals in experimental psychology and behavioral analysis.