Enjoy fast, free delivery, exclusive deals, and award-winning movies & TV shows with Prime
Try Prime
and start saving today with fast, free delivery
Amazon Prime includes:
Fast, FREE Delivery is available to Prime members. To join, select "Try Amazon Prime and start saving today with Fast, FREE Delivery" below the Add to Cart button.
Amazon Prime members enjoy:- Cardmembers earn 5% Back at Amazon.com with a Prime Credit Card.
- Unlimited Free Two-Day Delivery
- Streaming of thousands of movies and TV shows with limited ads on Prime Video.
- A Kindle book to borrow for free each month - with no due dates
- Listen to over 2 million songs and hundreds of playlists
- Unlimited photo storage with anywhere access
Important: Your credit card will NOT be charged when you start your free trial or if you cancel during the trial period. If you're happy with Amazon Prime, do nothing. At the end of the free trial, your membership will automatically upgrade to a monthly membership.
-9% $18.20$18.20
Ships from: Amazon.com Sold by: Amazon.com
$14.99$14.99
Ships from: Amazon Sold by: KAYLEY'S PRIME STORE
Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet, or computer - no Kindle device required.
Read instantly on your browser with Kindle for Web.
Using your mobile phone camera - scan the code below and download the Kindle app.
OK
Probably Approximately Correct 1st Edition
Purchase options and add-ons
How does life prosper in a complex and erratic world? While we know that nature follows patterns -- such as the law of gravity -- our everyday lives are beyond what known science can predict. We nevertheless muddle through even in the absence of theories of how to act. But how do we do it?
In Probably Approximately Correct, computer scientist Leslie Valiant presents a masterful synthesis of learning and evolution to show how both individually and collectively we not only survive, but prosper in a world as complex as our own. The key is "probably approximately correct" algorithms, a concept Valiant developed to explain how effective behavior can be learned. The model shows that pragmatically coping with a problem can provide a satisfactory solution in the absence of any theory of the problem. After all, finding a mate does not require a theory of mating. Valiant's theory reveals the shared computational nature of evolution and learning, and sheds light on perennial questions such as nature versus nurture and the limits of artificial intelligence.
Offering a powerful and elegant model that encompasses life's complexity, Probably Approximately Correct has profound implications for how we think about behavior, cognition, biological evolution, and the possibilities and limits of human and machine intelligence.
- ISBN-109780465060726
- ISBN-13978-0465060726
- Edition1st
- Publication dateNovember 14, 2014
- LanguageEnglish
- Dimensions5.5 x 0.52 x 8.25 inches
- Print length207 pages
Frequently bought together
Customers who viewed this item also viewed
Editorial Reviews
About the Author
Product details
- ASIN : 0465060722
- Publisher : Basic Books; 1st edition (November 14, 2014)
- Language : English
- Paperback : 207 pages
- ISBN-10 : 9780465060726
- ISBN-13 : 978-0465060726
- Item Weight : 2.31 pounds
- Dimensions : 5.5 x 0.52 x 8.25 inches
- Best Sellers Rank: #389,468 in Books (See Top 100 in Books)
- #226 in Mathematics History
- #666 in Artificial Intelligence & Semantics
- #1,226 in History & Philosophy of Science (Books)
- Customer Reviews:
About the author
Discover more of the author’s books, see similar authors, read author blogs and more
Customer reviews
Customer Reviews, including Product Star Ratings help customers to learn more about the product and decide whether it is the right product for them.
To calculate the overall star rating and percentage breakdown by star, we don’t use a simple average. Instead, our system considers things like how recent a review is and if the reviewer bought the item on Amazon. It also analyzed reviews to verify trustworthiness.
Learn more how customers reviews work on Amazon-
Top reviews
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
In brilliant fashion, Valiant twines natural (as in nature) problem solving and learning with the algorithmic processes of neural learning, and potentially machine learning (redefined), and sneakily hints at how the brain can process systems of dynamic partial diffential equations as matrix calculus without us even knowing it! If you've ever wondered how your brain can hold dual uncertainties (time/motion or frequency/time etc.) constant with PDE's (Fourier transforms) as you cross a street, without your "conscious" mind even being able to solve a partial differential without peeking at the text examples (let alone a Fourier inverse), this amazing book finally gives the closest I've ever seen to a believable answer. WOW are we EVER smart without "knowing" it!!! One of the many "ahas" is how "non experts" (eg our "conscious" brains) can invent things like calculus.
There's no advanced LaTex such as complex exponential superscript equations for e-readers to bugger up, so don't hesitate to get this on Kindle. There are polynomials and subscripts, but my Fire digested them just fine. A few of the many diagrams, tables and illustrations are too tiny to view, but a double tap takes care of that. Yes, the underlying math "discussed" really is post grad in some cases, but the author doesn't burden us with that level of notation, choosing instead to describe verbally (and with at most inequalities and a few polynomials and tables) the much simpler underlying "ecorithm" (algorithms that learn from their environment).
This book is relevant on too many levels to thoroughly list, but just a few include psych, engineering, algorithms, computational complexity, machine learning, AI, dynamic systems, education, consciousness, neurology, math... and onward. For non math major "lay" readers, the text is crisp, clear, readable/studyable with a nice pace and stories/illustrations that make it an unlikely but well written page turner. Strangely also, I truly believe it will appeal to both lay and pro readers/researchers -- the author strikes a very unusual balance with deep computational examples while not coming off as a show off-- one of the best teachers you'll ever want to meet, or if you're a technical author, emulate.
A bunch of books have now been written about how algorithms are taking over the world-- and how "unseen robots" (smart phones, cars and 777's) really are "thinking." This is better than the whole group of them combined! If you want a peek into your great great grandkids' planet-- get this asap! There are sincerely numerous new insights - discoveries - revelations on each page. The connections described are being researched in many fields right now, but silos prevent a lot of the overlaps between disciplines this author has spotted. They say Poincaire was the last great generalist-- this book makes me wonder. Even so, the author is humble in asking us to question HIS insights and discoveries every time he posits one as novel-- a true scholar.
A NOTE ABOUT COPING: Do NOT mistake the publisher's statements about "how to cope" with some self help promo or advice book. This is a very well written, but technical book about learning algorithms (usually relatively short "guiding" programs that tell other programs what to do), NOT coping in the usual sense of getting by strategies. Coping here refers more to how algorithms and organisms (yes, including us) can "navigate" environments too complex to understand, with shortcuts and guesstimates that work practically.
Author/Publisher: MORE! Expand for another 300 pages in your next edition! DO a version with the PDE's and pseudo code for those of us that don't mind trying to trudge through them.
Library Picks reviews only for the benefit of Amazon shoppers and has nothing to do with Amazon, the authors, manufacturers or publishers of the items we review. We always buy the items we review for the sake of objectivity, and although we search for gems, are not shy about trashing an item if it's a waste of time or money for Amazon shoppers. If the reviewer identifies herself, her job or her field, it is only as a point of reference to help you gauge the background and any biases.
The book's thesis in a few words: cognitive concepts are computational, and they are acquired by a learning process, before and after birth. Nature, the grand designer, uses ecorithms to guide this process - systems whose functioning and whose parameters are learned and evolved, as opposed to written down once (like algorithms). The processes of learning, evolution and reasoning are the building blocks of ecorithms.
This, in and of itself, is not a new framework. Open any artificial intelligence textbook, and the table of contents will be organized into algorithms for "learning" and "reasoning". So nothing new there. But then, the book launches into an excellent, simple and mind-blowing thought experiment: what if nature were simply relying on the same simple learning algorithms that we as humans have been researching, with the same constraints - and evolution is just that formal learning process in action? And then: given all we know about the parameters of these learning algorithms, would evolution have been mathematically possible?
To answer that, the author goes into some detail on computational complexity theory. Computer science has shown that there are many seemingly simple processes that aren't solvable in polynomial time - meaning, if you make them big enough, solving them will take longer than the universe existed. The question of the shortest overall path in visiting all cities in a particular geography is such a problem. So if it is so easy to mathematically prove that so many really simple problems aren't solvable in the time the universe existed, how would it even be remotely possible that evolution build something as complex as the human brain in an even shorter time frame?
The book then essentially explores areas of machine learning just deep enough to show that it probably would be possible. There are enough real-world functions of the "probably approximately correct"-learnable class that are learnable in polynomial time, and algorithms that do the learning that we already know (and use) today, that it's imaginable that nature relies on variants of those. The book has some strong tidbits it throws out in the course of discussing this. For example, it turns out that parity functions (deciding, without counting, whether something is odd or even) aren't PAC-learnable. So far, so satisfying a read.
One of the book's drawbacks is that a lot of the details are left open. In the author's thesis, the genome and our protein networks somehow encode the parameters of the learning algorithms nature uses. But of course we have no idea how that actually happens (and the book doesn't pretend that it knows). Another drawback is that the book seemingly can't quite decide on its audience: is it pop science or more serious work? It oscillates strangely between being very concrete and being hand-wavy: for example, when discussing the limits of machine learning (semantics, brittleness, complexity, grounding), there isn't anything offered in terms of why machine learning is so brittle (just try Apple's Siri). It also somewhat casually throws around ideas that are mind-blowing but totally unproven: for example, it is known that our working memory can only hold 7 +/- 2 objects at any point in time. The author argues that this is by design, so that the subsequent learning algorithms have an easier time picking up features. That's a pretty cool line of thinking, because it would suggest that nature uses the same heuristics that we as computer scientists use when tackling a learning problem (reduction in features and dimensionality). But it's also totally unproven that THIS is why we have limited working memory, or that THIS is what it does. The book also doesn't go into any depths on learning algorithms we already know, even though a lot of the known algorithms actually have pretty simple intuitions underlying them that could nicely be treated for a non-computer science audience.
But overall, there are some awesome thought starters in this book. It is not always an easy read. But certainly worth it.
Top reviews from other countries
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.