Hardcover

ISBN 10: 0198524277 ISBN 13: 9780198524274

Publisher: Oxford University Press, 1998

Connectionism is a way of modeling how the brain uses streams of sensory inputs to understand the world and produce behavior, based on cognitive processes which actually occur. This book describes the principles, and their application to explaining how the brain produces speech, forms memories and recognizes faces, how intellect develops, and how it deteriorates after brain damage. The models range from some well-known classics to others at the frontiers of current research. Also included is a disk with the software for running tlearn, a user-friendly simulator for connectionist modeling of cognitive processes, which will run on either PCs or Macs. Written by leading researchers in their field, this first up-to-date textbook on connectionist modeling, will provide an essential and accessible introduction to the field.

About the Author:

Peter McLeod, Kim Plunkett, and Edmund T. Rolls are all at Oxford University.

Review:

"McLeod, Plunkett, and Rolls provide an excellent, up-to-date introduction to parallel-distributed processing models, and their application to a wide range of issues in cognitive neuroscience, psycholinguistics, and developmental psychology. . . . The presentation is clear and self-contained, making this text an excellent choice for introducing connectionist/parallel distributed processing models to students in psychology, cognitive science, and cognitive neuroscience." --James L. McClelland, Carnegie Mellon University

"Connectionism has provided the study of cognition with its most important new theoretical methods of the last twenty years. However, to most students its models have just been a forbidding mass of abstractions. This book provides a simple introduction to the applications of connectionism to cognition. Written by leading experts in areas from neurobiology through cognitive psychology to developmental psychology and psycholinguistics, it provides a definitive view on the scientific utility of the approach as well as a lucid introduction to its technical aspects. For the first time, connectionism should become generally accessible to all students of cognition." --Tim Shallice, University College London

"This book is designed as an introduction to neural networks for undergraduate and beginning graduate students. The first seven chapters deal with beginning-level concepts, and the last eight chapters are primarily devoted to applications. The applications include discussions of syntactic acquisition rules, production of speech, episodic memories, and cognitive development. The book is an excellent introduction for students who learn best with a 'hand-on' approach. The book contains numerous examples and exercises with a software system called TLEARN. The software (which is included with the book) is a connectionist modeling package that provides a graphical interface for the back-propagation class of network models."--Journal of Mathematical Psychology

"Perhaps it is a sign of the maturity of neural networks research that it is only very recently that decent textbooks for psychologists have begun to appear: Introduction to connectionist modelling of cognitive processes (henceforth, Introduction) is such a textbook. In the main, the exposition is very clear, and the many figures and diagrams make the difficult material surprisingly easy to follow. . . . Overall, my feeling is that Introduction is a very useful text, and, for those of us who have struggled to teach connectionism to psychology undergraduates, it is something of a godsend."--The Quarterly Journal of Experimental Psychology