Qty:1
  • List Price: $23.00
  • Save: $3.34 (15%)
FREE Shipping on orders over $35.
Only 5 left in stock (more on the way).
Ships from and sold by Amazon.com.
Gift-wrap available.
FREE Shipping on orders over $35.
Used: Very Good | Details
Condition: Used: Very Good
Comment: clean and solid inside and out
Have one to sell? Sell on Amazon
Flip to back Flip to front
Listen Playing... Paused   You're listening to a sample of the Audible audio edition.
Learn more
See this image

The Algebraic Mind: Integrating Connectionism and Cognitive Science (Learning, Development, and Conceptual Change) Paperback – January 24, 2003


See all 3 formats and editions Hide other formats and editions
Amazon Price New from Used from
Paperback
"Please retry"
$19.66
$12.30 $7.59


Frequently Bought Together

The Algebraic Mind: Integrating Connectionism and Cognitive Science (Learning, Development, and Conceptual Change) + The Birth of the Mind: How a Tiny Number of Genes Creates The Complexities of Human Thought + Kluge: The Haphazard Evolution of the Human Mind
Price for all three: $44.23

Buy the selected items together

NO_CONTENT_IN_FEATURE

Best Books of the Month
Best Books of the Month
Want to know our Editors' picks for the best books of the month? Browse Best Books of the Month, featuring our favorite new books in more than a dozen categories.

Product Details

  • Series: Learning, Development, and Conceptual Change
  • Paperback: 240 pages
  • Publisher: A Bradford Book (January 24, 2003)
  • Language: English
  • ISBN-10: 0262632683
  • ISBN-13: 978-0262632683
  • Product Dimensions: 9.1 x 5.5 x 0.4 inches
  • Shipping Weight: 14.4 ounces (View shipping rates and policies)
  • Average Customer Review: 5.0 out of 5 stars  See all reviews (2 customer reviews)
  • Amazon Best Sellers Rank: #1,251,239 in Books (See Top 100 in Books)

Editorial Reviews

Review

In The Algebraic Mind, Marcus dives into the difficult waters of the connectionist-symbolic debate.

(Kenneth J. Kurtz Cognitive Sciences Society Newsletter)

From the Back Cover

"The Algebraic Mind is a rare and invaluable achievement, which should be required reading for cog nitive scientists, cognitive neuroscientists, and researchers in artificial intelligence."
--Steven Pinker, Peter de Florez Professor at MIT, and author of How the Mind Works and Words and Rules.

"This is a beautifully clear, fiercely argued book, and it will have a huge influence on how resea rchers from a range of different perspectives think about the nature of cognition and development."
-- Paul Bloom, Professor, Department of Psychology, Yale University

"a masterpiece of clear exposition from someone who has thought long and deeply about these questions."
-- C. R. Gallistel, Professor of Psychology, Rutgers University --This text refers to an out of print or unavailable edition of this title.


More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

5.0 out of 5 stars
5 star
2
4 star
0
3 star
0
2 star
0
1 star
0
See both customer reviews
Share your thoughts with other customers

Most Helpful Customer Reviews

16 of 17 people found the following review helpful By Todd I. Stark VINE VOICE on March 8, 2004
Format: Paperback
The Algebraic Mind is a technical analysis of what kind of computational device it would take to act like a human mind. What are the building blocks of the mind, and how can they be implemented in a brain?
Interweaving the lessons of the two traditions of cognitive science (symbol processing and connectionist networks), Gary Marcus concludes that connectionist networks are the right approach, but that current designs are not adequate.
In particular, Marcus shows the limitations of back propagation algorothms and of multilayer perceptron networks that have no initial structure and must learn everything from experience. This, he points out in the preface, has led others in the field to mistakenly assume he is anti-connectionist in general. This reveals the originality of his proposal. Rather than abandoning connectionism, Marcus proposes an original compromise, a growth path to a new kind of connnectionist network, one that can also act like a symbol processor.
For example, back propagation and similar learning algorithms used in current neural networks (multilayer perceptron models using multiple nodes to represent a variable) simply do not allow these networks to generalize abstract relations freely from experience the way biological brains are able to do in certain circumstances. Marcus argues tht such free generalization is essential to human thought, yet a serious problem for current networks.
Another limitation of current networks is in robustly representing complex relations between bits of knowledge. A third key limitation of current neural net models identified by Marcus is that they are generally not able to keep track of individuals separately from kinds.
Read more ›
Comment Was this review helpful to you? Yes No Sending feedback...
Thank you for your feedback. If this review is inappropriate, please let us know.
Sorry, we failed to record your vote. Please try again
16 of 18 people found the following review helpful By A Customer on March 18, 2004
Format: Paperback
This book tackles one of the most important (and poorly understood) questions in cognitive science: What is the form of human mental representation? Notice that this is nothing short of asking, what's in a mind such that it should think? ..., this question is not a simple one, it has by no means been answered, and there is raging debate in cognitive science as to what its answer is. ...
Traditional connectionist networks that learn by back-propagation or related algorithms do not implement symbol systems in the classical sense. That is, they do not perform computations as the execution of explicit abstract rules over an alphabet of symbolic primitives and recursively specified combinations of these symbols, and they do not variablize values. For most connectionist models, this is entirely intentional. Traditional connectionists seek explicitly to build networks that are not symbol systems because they believe that minds just don't work that way, and the evidence they cite is the success of their intentionally sub-symbolic models. In fact, this opinion is the prevailing one in the field of cognitive modeling.
What Marcus (and others) is arguing, is that what is required is not the elimination of symbol systems as models of cognition, but rather models that seek to implement them on neurally realistic substrates (like models composed of simple processing units that operate in parallel). His argument is cogent, convincing and decidedly well informed. It is for this reason that this book is such an accomplishment.
Comment Was this review helpful to you? Yes No Sending feedback...
Thank you for your feedback. If this review is inappropriate, please let us know.
Sorry, we failed to record your vote. Please try again