Mardigian Library
Ask a QuestionMy Library Account
Search Library Catalog - Books, DVDs & More
Limit to available
More Searches
Limit results to available items
Find more results:
Search MelCat
More Information
Valiant, Leslie
Probably approximately correct : nature's algorithms for learning and prospering in a complex world / Leslie Valiant
Alternate Title Nature's algorithms for learning and prospering in a complex world
New York : Basic Books, c2013
book jacket
Location Call Number Status
 3rd Floor  BF39.3 .V35 2013    AVAILABLE
Subject(s) Human behavior -- Mathematical models
Nature -- Mathematical models
Mathematics in nature
Physical Description x, 195 p. : ill. ; 25 cm
Note Includes bibliographical references (p. 175-184) and index
Contents Ecorithms -- Prediction and adaptation -- The computable: not everything that can be defined can be computed -- Mechanistic explanations of nature: what might we look for? -- The learnable: how can one draw general lessons from particular experiences? -- The evolvable: how can complex mechanisms evolve from simpler ones? -- The deducible: how can one reason with imprecise concepts? -- Humans as ecorithms -- Machines as ecorithms: why is artificial intelligence difficult to achieve? -- Questions
Summary Provides a model of how effective behavior can be learned even in a world as complex as our own, shedding new light on human nature

Mardigian Library, 4901 Evergreen Rd.
Dearborn, MI 48128-1491 313-593-5400 fax 313-593-5561
The Regents of the University of Michigan | Non-Discrimination Policy
Copyright © The University of Michigan - Dearborn • 4901 Evergreen Road • Dearborn, Michigan 48128 • 313-593-5000
The University of Michigan - Ann Arbor | The University of Michigan - Flint | SITEMAP | DIRECTORY | CONTACT