Features
- Cover Type: Hard Cover with 1344 pages
- Published by: The MIT Press
- Edition: 2nd Edition November 15, 2002
- Written in: English
- ISBN 10 Number: 0262011972
- ISBN 13 Number: 978-0262011976
-
Book Dimensions:
11.1 x 8.6 x 2.2 inches
- Weighs: 6.4 pounds
Product Description
Dramatically updating and extending the first edition, published in 1995, the second edition of
The Handbook of Brain Theory and Neural Networks presents the enormous progress made in recent years in the many subfields related to the two great questions: How does the brain work? and, How can we build intelligent machines?
Once again, the heart of the book is a set of almost 300 articles covering the whole spectrum of topics in brain theory and neural networks. The first two parts of the book, prepared by Michael Arbib, are designed to help readers orient themselves in this wealth of material. Part I provides general background on brain modeling and on both biological and artificial neural networks. Part II consists of "Road Maps" to help readers steer through articles in part III on specific topics of interest. The articles in part III are written so as to be accessible to readers of diverse backgrounds. They are cross-referenced and provide lists of pointers to Road Maps, background material, and related reading.
The second edition greatly increases the coverage of models of fundamental neurobiology, cognitive neuroscience, and neural network approaches to language. It contains 287 articles, compared to the 266 in the first edition. Articles on topics from the first edition have been updated by the original authors or written anew by new authors, and there are 106 articles on new topics.
Book Info
Comprehensive text charts the progress made in recent years in answering the questions 'How does the brain work?' and 'How can we build intelligent machines?' Articles are presented in alphabetical order by title. Part one covers background, part two, brain theory and neural networks, and part three includes the articles. Previous edition: c1995.
Reader Reviews
This review is from: The Handbook of Brain Theory and Neural Networks (Bradford Book) (Paperback)
Look through this book to convince yourself that an exact brain theory does not exist. The arrangement of the articles by the first letter of their title tells it all (consider classifying animals by the first letter of their name). The editors wrongly assume that mathematical methods equal theory; actually, theory is a small conceptual tent under which a large number of experimentally established facts can be gathered. In most cases, mathematics is a very useful tool in pitching this tent, but it has little to do with the tent itself. An exact theory of the brain may be possible and we are in dire need of it. Unfortunately, nobody has come up with it yet. This book is an encyclopedia of various mathematical methods that have been used to solve various neuroscience problems. These methods and solutions are as diverse as the problems themselves. Don't look for common themes in this book. If you are looking for a unified brain theory, you'll be much better off reading standard neuroscience textbooks. I do hope one day we'll be able to cast these vague ideas into something precise and, most likely, mathematical. Sadly, not today. I own a copy of this book and use it to remind me why and how we have failed so far. It should be kept in mind that it is not at all clear that "neural" networks can emulate consciousness. They may or they may not. Firstly, a single neuron resembles a computer processor in its complexity and is a constantly evolving entity. Secondly, only 10% of brain cells are neurons and the remaining 90% (glial cells) now too appear to be involved in information processing. At a more fundamental level, consciousness may be less algorithmic and computational than we expect. Finally, the brain and the reality "outside the brain" are a two-way street. As the great neuroscientist Cajal put it, "As long as our brain remains an arcanum, the Universe, a reflection of its structure, will also be a mystery". If we assume the brain analyzes something, we need to define a reality independent of this analysis -- a hardly possible task if standard "input-output" approaches are used. If the title of this book were "Current Mathematical Methods in Neurosciences", I'd have no problem giving it five stars. November 2005: The chapters in the second edition are still arranged alphabetically. I refuse to believe neuro-mathematicians cannot think more coherently. One final note for those looking for serious conceptual advances on the theoretical front: do no miss "Spikes: Exploring the Neural Code" (edited by F. Rieke) and "Decisions, Uncertainty, and the Brain: The Science of Neuroeconomics" by Paul Glimcher.
Comment | |
(Report this)
Search for books at
