About the Book
This groundbreaking monograph offers a mechanistic theory of therepresentation and use of semantic knowledge, integrating the strengths andovercoming many of the weaknesses of hierarchical, categorization-based approaches, similarity-based approaches, and the approach often called "theory theory." Buildingon earlier models by Geoffrey Hinton in the 1980s and David Rumelhart in the early1990s, the authors propose that performance in semantic tasks arises through thepropagation of graded signals in a system of interconnected processing units. Therepresentations used in performing these tasks are patterns of activation acrossunits, governed by weighted connections among them. Semantic knowledge is acquiredthrough the gradual adjustment of the strengths of these connections in the courseof day-to-day experience.The authors show how a simple computational model proposedby Rumelhart exhibits a progressive differentiation of conceptual knowledge, paralleling aspects of cognitive development seen in the work of Frank Keil and JeanMandler. The authors extend the model to address aspects of conceptual knowledgeacquisition in infancy, disintegration of conceptual knowledge in dementia, "basic-level" effects and their interaction with expertise, and many findingsintroduced to support the idea that semantic cognition is guided by naive, domain-specific theories.
Review :
"A fascinating exploration of the conceptual systems that emerge when a neural network is trained to predict the properties of objects. Rogers and McClelland show that incremental, error-driven learning leads to internal distributed representations that explain a whole variety of empirical phenomena. Their network exhibits remarkable common sense in the way it generalizes, and distinctly human frailty in the way its knowledge disintegrates when it is physically degraded. The book uses very little technical jargon and the reasoning is clear, detailed, and compelling."--Geoffrey Hinton, FRS, Canada Research Chair in Machine Learning, Department of Computer Science, University of Toronto
"This book deals with one of the central questions in cognitive science: What is the nature of semantic knowledge? The computational framework that Rogers and McClelland propose, while elegant in its simplicity, provides deep insights into the development (and loss, with brain damage) of category structure, causal knowledge, and semantic organization. In providing both a mechanistic processing account as well as an interpretation of the principles underlying the mechanism's properties, Rogers and McClelland explain a wide range of complex phenomena that have hitherto resisted a unified account. This is a very important book."--Jeff Elman, Professor of Cognitive Science, University of California, San Diego
"This important book pushes connectionism into the true heartland of cognitive science: human semantic cognition. Through an elegant weave of empirical reviews and specific PDP models, topics in adult cognition, cognitive development, and neuropsychology are brought together and underlying computational principles revealed. Destined to become an influential landmark in the field, the book will be essential reading for a wide range of cognitive scientists."--Mark Johnson, Director of the Centre for Brain and Cognitive Development, University of London
"This is a fascinating book. It explores the ability of PDP models to simulate many behavioral phenomena thought to arise from properties of semantic and conceptual structure. These phenomena include: differentiation of taxonomic structures in development, the basic level of categorization, conceptual coherence, illusory correlations, inductive projection, conceptual change, domain specificity, and the influences of causal knowledge and intuitive theories. Both fans and foes of PDP approaches will want to study this ambitious and innovative application of connectionist learning models."--Frank C. Keil, Professor, Department of Psychology, Yale University
& quot; A fascinating exploration of the conceptual systems that emerge when a neural network is trained to predict the properties of objects. Rogers and McClelland show that incremental, error-driven learning leads to internal distributed representations that explain a whole variety of empirical phenomena. Their network exhibits remarkable common sense in the way it generalizes, and distinctly human frailty in the way its knowledge disintegrates when it is physically degraded. The book uses very little technical jargon and the reasoning is clear, detailed, and compelling.& quot; --Geoffrey Hinton, FRS, Canada Research Chair in Machine Learning, Department of Computer Science, University of Toronto
& quot; This book deals with one of the central questions in cognitive science: What is the nature of semantic knowledge? The computational framework that Rogers and McClelland propose, while elegant in its simplicity, provides deep insights into the development (and loss, with brain damage) of category structure, causal knowledge, and semantic organization. In providing both a mechanistic processing account as well as an interpretation of the principles underlying the mechanism& rsquo; s properties, Rogers and McClelland explain a wide range of complex phenomena that have hitherto resisted a unified account. This is a very important book.& quot; --Jeff Elman, Professor of Cognitive Science, University of California, San Diego
& quot; This important book pushes connectionism into the true heartland of cognitive science: human semantic cognition. Through an elegant weave of empirical reviews and specific PDP models, topics in adult cognition, cognitive development, and neuropsychology are brought together and underlying computational principles revealed. Destined to become an influential landmark in the field, the book will be essential reading for a wide range of cognitive scientists.& quot; --Mark Johnson, Director of the Centre for Brain and Cognitive Development, University of London
& quot; This is a fascinating book. It explores the ability of PDP models to simulate many behavioral phenomena thought to arise from properties of semantic and conceptual structure. These phenomena include: differentiation of taxonomic structures in development, the basic level of categorization, conceptual coherence, illusory correlations, inductive projection, conceptual change, domain specificity, and the influences of causal knowledge and intuitive theories. Both fans and foes of PDP approaches will want to study this ambitious and innovative application of connectionist learning models.& quot; --Frank C. Keil, Professor, Department of Psychology, Yale University
" A fascinating exploration of the conceptual systems that emerge when a neural network is trained to predict the properties of objects. Rogers and McClelland show that incremental, error-driven learning leads to internal distributed representations that explain a whole variety of empirical phenomena. Their network exhibits remarkable common sense in the way it generalizes, and distinctly human frailty in the way its knowledge disintegrates when it is physically degraded. The book uses very little technical jargon and the reasoning is clear, detailed, and compelling." --Geoffrey Hinton, FRS, Canada Research Chair in Machine Learning, Department of Computer Science, University of Toronto
" This book deals with one of the central questions in cognitive science: What is the nature of semantic knowledge? The computational framework that Rogers and McClelland propose, while elegant in its simplicity, provides deep insights into the development (and loss, with brain damage) of category structure, causal knowledge, and semantic organization. In providing both a mechanistic processing account as well as an interpretation of the principles underlying the mechanism’ s properties, Rogers and McClelland explain a wide range of complex phenomena that have hitherto resisted a unified account. This is a very important book." --Jeff Elman, Professor of Cognitive Science, University of California, San Diego
" This important book pushes connectionism into the true heartland of cognitive science: human semantic cognition. Through an elegant weave of empirical reviews and specific PDP models, topics in adult cognition, cognitive development, and neuropsychology are brought together and underlying computational principles revealed. Destined to become an influential landmark in the field, the book will be essential reading for a wide range of cognitive scientists." --Mark Johnson, Director of the Centre for Brain and Cognitive Development, University of London
" This is a fascinating book. It explores the ability of PDP models to simulate many behavioral phenomena thought to arise from properties of semantic and conceptual structure. These phenomena include: differentiation of taxonomic structures in development, the basic level of categorization, conceptual coherence, illusory correlations, inductive projection, conceptual change, domain specificity, and the influences of causal knowledge and intuitive theories. Both fans and foes of PDP approaches will want to study this ambitious and innovative application of connectionist learning models." --Frank C. Keil, Professor, Department of Psychology, Yale University
--Frank C. Keil, Professor, Department of Psychology, Yale University
--Geoffrey Hinton, FRS, Canada Research Chair in Machine Learning, Department of Computer Science, University of Toronto
--Jeff Elman, Professor of Cognitive Science, University of California, San Diego
--Mark Johnson, Director of the Centre for Brain and Cognitive Development, University of London
