Neural Computing Architectures: The Design of Brain-like Machines - Hardcover

Aleksander, Igor

Hardcover

ISBN 10: 0946536473 ISBN 13: 9780946536474

Publisher: North Oxford Academic Publishing Co Ltd, 1989

Synopsis

McClelland and Rumelhart's Parallel Distributed Processing was the first book to present a definitive account of the newly revived connectionist/neural net paradigm for artificial intelligence and cognitive science. While Neural Computing Architectures addresses the same issues, there is little overlap in the research it reports. These 18 contributions provide a timely and informative overview and synopsis of both pioneering and recent European connectionist research. Several chapters focus on cognitive modeling; however, most of the work covered revolves around abstract neural network theory or engineering applications, bringing important complementary perspectives to currently published work in PDP. In four parts, chapters take up neural computing from the classical perspective, including both foundational and current work; the mathematical perspective (of logic, automata theory, and probability theory), presenting less well-known work in which the neuron is modeled as a logic truth function that can be implemented in a direct way as a silicon read only memory. They present new material both in the form of analytical tools and models and as suggestions for implementation in optical form, and summarize the PDP perspective in a single extended chapter covering PDP theory, application, and speculation in US research. Each part is introduced by the editor.

About this title

Synopsis

Over the past few years neural computing (otherwise known as connectionism) has undergone a transformation; from being a half-forgotten backwater it has suddenly become a subject of intense interest. To date, however, most of the excitement has centered upon current research in the United States and this has tended to obscure two facts; firstly, that the history of neural computing can be traced back to the very origins of the digital computer itself, and secondly, that it is a field in which European researchers have made and are continuing to make a significant contribution. This book aims to remedy these misconceptions. It presents 16 specially-commissioned papers from European researchers, including theoreticians such as Tuevo Kohonen, Eduardo Caianiello and the editor Igor Aleksander. The contributions are arranged in three parts: the classical perspective; the logical perspective; and analysis and interpretation. The book stresses the more practically oriented approach which dominates European work on neural computing and includes an summary of existing PDP (Parallel Distributed Processing) methodology.

This book should be of interest to computer scientists, physicists, mathematicians, physiologists, psychologists and cognitive scientists.

About the Author

Igor Aleksander is Professor of Computer Science at Imperial College in London.

Edition details

• Publisher: North Oxford Academic Publishing Co Ltd
• Publication date: 1989
• Language: English
• ISBN 10: 0946536473
• ISBN 13: 9780946536474
• Binding: Hardcover
• Edition number: 1
• Number of pages: 320