An Introduction to Computational Learning Theory (MIT Press)

by Michael J. Kearns (Author), Umesh Vazirani (Author)

3 customer reviews

ISBN-13: 978-0262111935

ISBN-10: 0262111934

Why is ISBN important?

Trade in your item
Get a $15.21
Gift Card.

Trade in
Learn More

Have one to sell? Sell on Amazon

Buy used On clicking this link, a new layer will be open

$36.54 On clicking this link, a new layer will be open

Condition: Used - Good

In Stock. Sold by Free State Books

Access codes and supplements are not guaranteed with used items.

24 Used from $36.54

+ $3.99 shipping

Buy new On clicking this link, a new layer will be open

$63.00 On clicking this link, a new layer will be open

Only 6 left in stock (more on the way).

Ships from and sold by Amazon.com. Gift-wrap available.

Want it Thursday, Oct. 20? Order within and choose One-Day Shipping at checkout. Details

List Price: $70.00 Save: $7.00 (10%)

20 New from $63.00

FREE Shipping.

Turn on 1-Click ordering

Ship to:

Select a shipping address:

More Buying Choices

20 New from $63.00 24 Used from $36.54

44 used & new from $36.54

See All Buying Options

Free%20Two-Day%20Shipping%20for%20College%20Students%20with%20Amazon%20Student

Emphasizing issues of computational efficiency, Michael Kearns and Umesh Vazirani introduce a number of central topics in computational learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics.Computational learning theory is a new and rapidly expanding area of research that examines formal models of induction with the goals of discovering the common methods underlying efficient learning algorithms and identifying the computational impediments to learning.Each topic in the book has been chosen to elucidate a general principle, which is explored in a precise formal setting. Intuition has been emphasized in the presentation to make the material accessible to the nontheoretician while still providing precise arguments for the specialist. This balance is the result of new proofs of established theorems, and new presentations of the standard proofs.The topics covered include the motivation, definitions, and fundamental results, both positive and negative, for the widely studied L. G. Valiant model of Probably Approximately Correct Learning; Occam's Razor, which formalizes a relationship between learning and data compression; the Vapnik-Chervonenkis dimension; the equivalence of weak and strong learning; efficient learning in the presence of noise by the method of statistical queries; relationships between learning and cryptography, and the resulting computational limitations on efficient learning; reducibility between learning problems; and algorithms for learning finite automata from active experimentation.

An Introduction to Computational Learning Theory (MIT Press)

$63.00 FREE Shipping. Only 6 left in stock (more on the way). Ships from and sold by Amazon.com. Gift-wrap available.

Frequently Bought Together

Total price: $140.97

One of these items ships sooner than the other. Show details

Buy the selected items together

This item:An Introduction to Computational Learning Theory (MIT Press) by Michael J. Kearns Hardcover $63.00
Only 6 left in stock (more on the way).
Ships from and sold by Amazon.com.
FREE Shipping. Details
Pattern Recognition and Machine Learning (Information Science and Statistics) by Christopher Bishop Hardcover $77.97
In Stock.
Ships from and sold by Amazon.com.
FREE Shipping. Details

Customers Who Bought This Item Also Bought

Page 1 of 1 Start overPage 1 of 1

This shopping feature will continue to load items. In order to navigate out of this carousel please use your heading shortcut key to navigate to the next or previous heading.

Christopher Bishop

125

Hardcover
$77.97
Shai Shalev-Shwartz

11

Hardcover
$55.58
Trevor Hastie

76

in Bioinformatics
Hardcover
$71.92
Mehryar Mohri

9

Hardcover
$76.50
Thomas H. Cormen

418

in Computer Algorithms
Hardcover
$66.32
Stuart Russell

122

Hardcover
$153.89

Customers Viewing This Page May Be Interested In These Sponsored Links

(What's this?)

NO_CONTENT_IN_FEATURE

Product Details

Series: MIT Press
Hardcover: 221 pages
Publisher: The MIT Press (August 15, 1994)
Language: English
ISBN-10: 0262111934
ISBN-13: 978-0262111935
Product Dimensions: 7.1 x 0.6 x 9.2 inches
Shipping Weight: 1.4 pounds (View shipping rates and policies)
Average Customer Review: 4.7 out of 5 stars See all reviews (3 customer reviews)
Amazon Best Sellers Rank: #546,988 in Books (See Top 100 in Books)
- #167 in Books > Textbooks > Computer Science > Artificial Intelligence
- #375 in Books > Computers & Technology > Computer Science > AI & Machine Learning > Intelligence & Semantics
- #12378 in Books > Textbooks > Education

Would you like to update product info or give feedback on images?

Customers Viewing This Page May Be Interested In These Sponsored Links

(What's this?)

Customer Reviews

4.7 out of 5 stars

5 star		67%
4 star		33%
3 star		0%
2 star		0%
1 star		0%

Write a customer review

See all 3 customer reviews

Top Customer Reviews

This is interesting stuff

ByA customeron November 17, 2000

Format: Hardcover

Kearns is an impressive researcher, precise and succinct. The material on this book follows a tradition of careful proofs of fundamental issues in learning. I wouldn't think this is material of practical use; for that kind of material I'd recommend the new edition of Duda. Rather, Kearns is one of a team of researchers pushing the frontier of proving what is learnable and what is not, why some representations are good for learning and which are not, the dimensionality of the target problem (related to overfitting) working with prinpled definitions of what it is meant to learn borrowed from computational complexity theory.

0Comment 23 people found this helpful. Was this review helpful to you?YesNo

It turns out that complexity theorists have something valuable to say...

ByShiva Kaulon January 9, 2009

Format: Hardcover

...about machine learning since learning algorithms are, in fact, algorithms. At a high level, computational learning theory answers the same sort of questions as statistical learning theory ("What kind of guarantees can I make about my learning procedure? In what situations is learning possible?") with different tools and methodology. Trade in your operator equations, modes of convergence, and support vectors for boolean formulae, complexity classes, and quadratic residues, but don't worry; the trade is temporary, since the theories are complementary, and short-lived, since the book is easy and quick to read. At well under 200 large-type pages, you can mow through it armed with little besides Big-O notation, basic probability, and a few (IID) samples of your favorite stimulant.

In return for your mild effort, you will be acquainted with the PAC model of learning and techniques for reasoning about tractability, sample size, connections to well-known problems, etc. The best material, in my opinion, relates to the importance of problem representation and methods for establishing the difficulty of efficient predictability. Even the most unsatisfying material (the treatment of Occam's razor and the description of VC dimension) isn't stale, and wasn't really bad to start; this, despite the book's age (15 years in a 25 year old subfield), is most probably* a testament to the book's value as an approachable introduction.

* (As usual, some positive probability is reserved to indict the field's lack of advancement. But not much).

0Comment 12 people found this helpful. Was this review helpful to you?YesNo

So far so good

ByR. Smithon October 3, 2008

Format: Hardcover

The few chapters I have read of this book seem good. Good examples which is nice.

0Comment One person found this helpful. Was this review helpful to you?YesNo

Set up an Amazon Giveaway

Amazon Giveaway allows you to run promotional giveaways in order to create buzz, reward your audience, and attract new followers and customers. Learn more about Amazon Giveaway

This item: An Introduction to Computational Learning Theory (MIT Press)

Set up a giveaway

What Other Items Do Customers Buy After Viewing This Item?

Understanding Machine Learning: From Theory to Algorithms Hardcover

Shai Shalev-Shwartz

11

$55.58
Learning From Data Hardcover

Yaser S. Abu-Mostafa

116
The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics) Hardcover

Trevor Hastie

76

$71.92
Probably Approximately Correct: Nature's Algorithms for Learning and Prospering in a Complex World Paperback

Leslie Valiant

37

$11.99

Pages with Related Products. See and discover other items: power query

Conditions of Use
Privacy Notice
Interest-Based Ads

6pm Score deals on fashion brands	AbeBooks Rare Books & Textbooks	ACX Audiobook Publishing Made Easy	Alexa Actionable Analytics for the Web	Amazon Business Everything For Your Business	AmazonFresh Groceries & More Right To Your Door

AmazonGlobal Ship Orders Internationally	Home Services Handpicked Pros Happiness Guarantee	Amazon Inspire Free Digital Educational Resources	Amazon Video Direct Video Distribution Made Easy	Amazon Web Services Scalable Cloud Computing Services	Audible Download Audio Books

BeautyBar.com Prestige Beauty Delivered	Book Depository Books With Free Delivery Worldwide	Casa.com Kitchen, Storage & Everything Home	ComiXology Thousands of Digital Comics	CreateSpace Indie Print Publishing Made Easy	Diapers.com Everything But The Baby

DPReview Digital Photography	East Dane Designer Men's Fashion	Fabric Sewing, Quilting & Knitting	Goodreads Book reviews & recommendations	IMDb Movies, TV & Celebrities	Junglee.com Shop Online in India

Kindle Direct Publishing Indie Digital Publishing Made Easy	Prime Now FREE 2-Hour Delivery on Everyday Items	Prime Photos Unlimited Photo Storage Free With Prime	Shopbop Designer Fashion Brands	Soap.com Health, Beauty & Home Essentials	TenMarks.com Math Activities for Kids & Schools

Wag.com Everything For Your Pet	Warehouse Deals Open-Box Discounts	Whispercast Discover & Distribute Digital Content	Woot! Deals and Shenanigans	Yoyo.com A Happy Place To Shop For Toys	Zappos Shoes & Clothing

An Introduction to Computational Learning Theory (MIT Press)

Sorry, there was a problem.

Sorry, there was a problem.

Buy used On clicking this link, a new layer will be open $36.54 On clicking this link, a new layer will be open

Turn on 1-Click ordering

Buy new On clicking this link, a new layer will be open $63.00 On clicking this link, a new layer will be open

Turn on 1-Click ordering

or

or

Frequently Bought Together

Customers Who Bought This Item Also Bought

Customers Viewing This Page May Be Interested In These Sponsored Links

Product Details

Customers Viewing This Page May Be Interested In These Sponsored Links

Customer Reviews

Top Customer Reviews

Set up an Amazon Giveaway

What Other Items Do Customers Buy After Viewing This Item?

Buy used On clicking this link, a new layer will be open

$36.54 On clicking this link, a new layer will be open

Buy new On clicking this link, a new layer will be open

$63.00 On clicking this link, a new layer will be open