This volume provides an overview of a relatively neglected branch of connectionism known as localist connectionism. The singling out of localist connectionism is motivated by the fact that some critical modeling strategies have been more readily applied in the development and testing of localist as opposed to distributed connectionist models (models using distributed hidden-unit representations and trained with a particular learning algorithm, typically back-propagation). One major theme emerging from this book is that localist connectionism currently provides an interesting means of evolving from verbal-boxological models of human cognition to computer-implemented algorithmic models. The other central messages conveyed are that the highly delicate issue of model testing, evaluation, and selection must be taken seriously, and that model-builders of the localist connectionist family have already shown exemplary steps in this direction.

About the Author
Arthur Jacobs, Jonathan Grainger, Arthur M. Jacobs

Reviews

"..the book contains many excellent papers."
-Journal of Mathematical Psychology

"The editors have done a commendable job of laying out a general approach to psychological theory building and testing. Importantly, they have also done much to show how connectionist modeling can be linked to information processing approaches in psychological science."
-Contemporary Psychology

Book Information
ISBN 9781138002753
Author Jonathan Grainger
Format Paperback
Page Count 384
Imprint Psychology Press Ltd
Publisher Taylor & Francis Ltd
Weight(grams) 498g