Probably approximately correct, nature's algorithms for learning and prospering in a complex world, Leslie Valiant
Type
Label
Probably approximately correct, nature's algorithms for learning and prospering in a complex world, Leslie Valiant
Language
eng
Bibliography note
Includes bibliographical references (p. 175-184) and index
Illustrations
illustrations
Index
index present
Literary Form
non fiction
Main title
Probably approximately correct
Nature of contents
bibliography
Oclc number
811598820
Responsibility statement
Leslie Valiant
Sub title
nature's algorithms for learning and prospering in a complex world
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
Table Of 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