Probably approximately correct : nature’s algorithms for learning and prospering in a complex world / Leslie Valiant.

Valiant, Leslie.
New York : Basic Books, c2013.
Added to CLICnet on 06/27/2014


Check CLICnet for availability
Notes:

  • Includes bibliographical references (pages 175-184) and index.
  • 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.
  • 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.

Subjects:

Requested by Bloomberg, M

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>