Probably Approximately Correct

Nature's Algorithms for Learning and Prospering in a Complex World

Nonfiction, Computers, Advanced Computing, Artificial Intelligence, Computer Science, Science & Nature, Science, Biological Sciences, Evolution
Cover of the book Probably Approximately Correct by Leslie Valiant, Basic Books
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Leslie Valiant ISBN: 9780465037902
Publisher: Basic Books Publication: June 4, 2013
Imprint: Basic Books Language: English
Author: Leslie Valiant
ISBN: 9780465037902
Publisher: Basic Books
Publication: June 4, 2013
Imprint: Basic Books
Language: English

We have effective theories for very few things. Gravity is one, electromagnetism another. But for most things—whether as mundane as finding a mate or as major as managing an economy—our theories are lousy or nonexistent. Fortunately, we don't need them, any more than a fish needs a theory of water to swim; we're able to muddle through. But how do we do it? In Probably Approximately Correct, computer scientist Leslie Valiant presents a theory of the theoryless. The key is “probably approximately correct” learning, Valiant's model of how anything can act without needing to understand what is going on. The study of probably approximately correct algorithms reveals the shared computational nature of evolution and cognition, indicates how computers might possess authentic intelligence, and shows why hacking a problem can be far more effective than developing a theory to explain it. After all, finding a mate is a lot more satisfying than finding a theory of mating.

Offering an elegant, powerful model that encompasses all of life's complexity, Probably Approximately Correct will revolutionize the way we look at the universe's greatest mysteries.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

We have effective theories for very few things. Gravity is one, electromagnetism another. But for most things—whether as mundane as finding a mate or as major as managing an economy—our theories are lousy or nonexistent. Fortunately, we don't need them, any more than a fish needs a theory of water to swim; we're able to muddle through. But how do we do it? In Probably Approximately Correct, computer scientist Leslie Valiant presents a theory of the theoryless. The key is “probably approximately correct” learning, Valiant's model of how anything can act without needing to understand what is going on. The study of probably approximately correct algorithms reveals the shared computational nature of evolution and cognition, indicates how computers might possess authentic intelligence, and shows why hacking a problem can be far more effective than developing a theory to explain it. After all, finding a mate is a lot more satisfying than finding a theory of mating.

Offering an elegant, powerful model that encompasses all of life's complexity, Probably Approximately Correct will revolutionize the way we look at the universe's greatest mysteries.

More books from Basic Books

Cover of the book Kingdoms of Faith by Leslie Valiant
Cover of the book An Iron Wind by Leslie Valiant
Cover of the book The Nuclear Sphinx of Tehran by Leslie Valiant
Cover of the book Experience the Message by Leslie Valiant
Cover of the book The Social Transformation of American Medicine by Leslie Valiant
Cover of the book Passed and Present by Leslie Valiant
Cover of the book And The World Closed Its Doors by Leslie Valiant
Cover of the book The Making of Modern Zionism by Leslie Valiant
Cover of the book Lesser Beasts by Leslie Valiant
Cover of the book Gonzo Marketing by Leslie Valiant
Cover of the book Taking Away the Distance by Leslie Valiant
Cover of the book University, Inc. by Leslie Valiant
Cover of the book Goddess of Anarchy by Leslie Valiant
Cover of the book The Choice Effect by Leslie Valiant
Cover of the book Killing Monsters by Leslie Valiant
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy