Probably Approximately Correct: Nature's Algorithms for Learning and Prospering in a Complex World Hardcover – 4 Jun 2013
- Choose from over 13,000 locations across the UK
- Prime members get unlimited deliveries at no additional cost
- Find your preferred location and add it to your address book
- Dispatch to this address when you check out
Customers who viewed this item also viewed
Customers who bought this item also bought
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
"This remarkable book is carefully constructed to give the lay person a sense of subtle problems in mathematics and artificial intelligence, and offers a framework for biologists and computer scientists to use in jointly investigating the most fascinating and enigmatic biological questions."--Marc Kirschner, Chair, Department of Systems Biology, Harvard Medical School, and coauthor of "The Plausibility of Life: Resolving Darwin's Dilemma"
"This book contains a lot of fresh thinking and elegant, nuanced ideas. It is more than probably approximately brilliant. I am amazed by how much insight has been packed into relatively few pages. Anyone interested in computation, learning, evolution, or human nature should find these pages extraordinarily stimulating and informative."--Stephen M. Kosslyn, Founding Dean, Minerva University, and former director, Center for Advanced Study in the Behavioral Sciences, Stanford University
"Ecorithms are algorithms that learn from interaction with their environment. This book provides a theoretical framework for understanding the power and limits of ecorithms and applies it to human cognition, biological evolution and artificial intelligence. It is elegantly written and will be accessible to a wide circle of readers."--Richard Karp, Turing Award winner and director, Simons Institute for the Theory of Computing, University of California, Berkeley
"This little book is hugely ambitious. It takes on the task of creating a quantitative, mathematical theory to explain all essential mechanisms governing the behavior of all living organisms: survival, learning, adaptation, evolution, cognition and intelligence. The suggested theory has all the characteristics of a great one. It is simple, general, and falsifiable, and moreover seems probably, approximately, correct!" --Avi Wigderson, Nevanlinna Prize winner and Professor of Mathematics, Institute for Advanced Study, Princeton
"The quest for machines (and codes) that ne
A leading computer scientist shows why understanding computation is the key to understanding lifeSee all Product description
Customers also shopped for
Showing 1-5 of 5 reviews
There was a problem filtering reviews right now. Please try again later.
Leslie Valiant sets out to show that it is computationally feasible for life to evolve its amazingly complex solutions to problems of survival, given the time (3.5bn years) and resource available. He shows, using a lot of maths concepts, that at the heart of evolution and learning there must be a relatively simple computation performed in a relatively simple processor that enables life to learn from examples and ultimately create sophisticated solutions that work (or persist). He explains that unlike computer-based computations, which are logical and algorithmic, life's computations are 'theory-less' in that they cannot apply generally outside the domain they have been learned in; they work tolerably in those domains - well enough for survival; they get better (fewer errors) when needed by adding learning from more examples (they adapt) - so they are robust in that they can be improved if needed and fail gracefully; the solutions aren't necessarily logical but they are powerful because the computation can powerfully chain solutions in a form of reasoning. This model can apply not just to evolution of persistent life forms but also to learning persistent ideas (knowledge). He calls these algorithms, ecorithms.
Along the way he offers all sorts of delightful insights, such as that life works on problems as if it was 'decrypting' the key to the answer.
Like many mathematicians, Valiant wants to show us the working before telling us the answer. I'd suggest reading this book back to front. Start with the Glossary to understand the language, then look at the notes to get an idea of the context, then go to section 7.7. where he finally reveals the exciting answer on how computation is done by evolution. Now you are ready to be told the story.
Despite difficulties in understanding quite a bit of the book I have, in common with some other reviewers, given it 5 stars for the various fascinating parts that I could follow.
The book covers a variety of topics including the Turing machine and complexity theory but I take the two main subjects to be computer learning (or Artificial Intelligence), and a theory of evolution based around genetic learning.
Humans learn and can perform complex operations without having any knowledge of an underlying theory of how something works – we do not need defined algorithms. Computers however need defined rules before they can do anything. Professor Valiant’s method of PAC (see the book title) is a way of looking at learning without having an exact formula or algorithm to get to an answer. I broadly understood the concept of PAC but can’t say I got any idea of how it could actually be used for computer learning.
Moving on from computers Professor Valiant applies PAC to the method of evolution.
Darwin’s Natural Selection, i.e. the stronger of random mutations winning out, has been challenged by Intelligent Design where some external agent, whether alien or God has influenced the development of DNA.
Professor Valiant maintains that the probability of the creation of DNA and subsequent evolution happening by chance is not mathematically justifiable.
He proposes that the evolution of DNA is controlled neither by chance nor by external design but by a learning feedback method he calls ecorithms, and he applies PAC to this.
Valiant coined the term "ecorithms" for the computational rules which help a system to learn through interactions with the environment. The book relates adaptation with learning (PAC), evolution and cognition in a common naturalistic computational framework. Recommended to anyone interested in how nature works and how its functioning relies on computational strategies.