Parallel Distributed Processing, Vol. 1: Foundations [Paperback]

David E. Rumelhart (Author), James L. McClelland (Author), PDP Research Group (Author)

Book Description

Publication Date: July 29, 1987 | Series: Parallel Distributed Processing (Book 1)

What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a new theory of cognition called connectionism that is challenging the idea of symbolic computation that has traditionally been at the center of debate in theoretical discussions about the mind.

The authors' theory assumes the mind is composed of a great number of elementary units connected in a neural network. Mental processes are interactions between these units which excite and inhibit each other in parallel rather than sequential operations. In this context, knowledge can no longer be thought of as stored in localized structures; instead, it consists of the connections between pairs of units that are distributed throughout the network.

Volume 1 lays the foundations of this exciting theory of parallel distributed processing, while Volume 2 applies it to a number of specific issues in cognitive science and neuroscience, with chapters describing models of aspects of perception, memory, language, and thought.

Editorial Reviews

Amazon.com Review

This two-volume work is now considered a classic in the field. It presents the results of the Parallel Distributed Processing (PDP) group's work in the early 1980s and provides a good overview of the earlier neural network research. The PDP approach (also known as connectionism among other things) is based on the conviction that various aspects of cognitive activity are thought of in terms of massively parallel processing. The first volume starts with the general framework and continues with an analysis of learning mechanisms and various mathematical and computational tools important in the analysis of neural networks. The chapter on backpropagation is written by Rumelhart, Hinton, and Williams, who codiscovered the algorithm in 1986. The second volume is written with a psychological and biological emphasis. It explores the relationship of PDP to various aspects of human cognition. The book is a comprehensive research survey of its time and most of the book's results and methods are still at the foundation of the neural network field. --This text refers to an out of print or unavailable edition of this title.

Review

"Rumelhart and McClelland propose that what is stored in memory is not specific facts or events, but rather the relationships between the various aspects of those facts or events as they are encoded in groupings of neuronal cells or patterns of cell activity." Daniel Coleman, The New York Times

See all Editorial Reviews

Product Details

• Paperback: 576 pages
• Publisher: A Bradford Book (July 29, 1987)
• Language: English
• ISBN-10: 026268053X
• ISBN-13: 978-0262680530
• Product Dimensions: 6 x 1.3 x 9 inches
• Shipping Weight: 1.9 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars  See all reviews (2 customer reviews)
• Amazon Best Sellers Rank: #421,493 in Books (See Top 100 in Books)

Most Helpful Customer Reviews

12 of 13 people found the following review helpful

5.0 out of 5 stars A Historic Milestone: A book for AI and machine learning June 22, 2001

By Zhe Chen

Format:Paperback

Though I believe I am not the first person writing the book review of this historic book, I still feel honored to encourage the new readers to read this one of most important AI research book published in 1986. The book edited by Rumlhart and McClelland was well organized and well written, comprised of a series of independent and interesting topics in neural network researches given by the dedicated authors. The editors themselves are also reputated authors in the connectionist community. The most results in that book never appeared in the past publications and represented the high-quality papers in the state-of-the-art research at that time. Many papers in that book rank the top position of citation rate even today, e.g. the paper about error backpropagation due to Rumelhart, Hinton and Williams. I also got to point out that the importance of the book not only lies in its scientific contribution, but also its philosophical meaning in the AI research (which is somehow influenced by the book 'Perceptrons' by Minsky and Pappert). The successful research results in that book showed people of the potential and new prospect of neural networks in different perspectives. From then on the second connectionist revolution has sprang and lasted today. Nowadays, people still can feel its leading influence by reading it. Upon reading the book again and again, you will always feel inspired at another new way (that is the value of a book!). Try it immediately.

In a word without exaggeration, the importance of this book to connectionist and AI researchers is like the Bible to Christians. Read it, enjoy it, once and again.

1 of 1 people found the following review helpful

5.0 out of 5 stars Classic and Influential February 1, 2008

By Touchstone

Format:Paperback

This book establishes the foundation mathematics and definitions of what are now called "neural networks". In 1986 these guys (on DARPA grants) figured out the basics of what is (in my opinion) the most significant advance in artifical intelligence since the 1960s. The book is a bit dry, as a fully rigorous academic text usually is, but the results speak for themselves - the techniques and approaches described in this book are used all over in some of the most challenging areas of AI - character, speech, and face recognition, surveilance, applicant screening, and so on.

Read it if you believe artifical intelligence is a bunch of hooey - I do, except this stuff.