Probably Approximately Correct: NatureÕs Algorithms for Learning and Prospering in a Complex WorldFrom a leading computer scientist, a unifying theory that will revolutionize our understanding of how life evolves and learns. 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. |
Contents
Summary | |
Prediction and Adaptation 13 | |
Not everything that can be defined can be computed 23 | |
What might we look for? 51 | |
How can one draw general lessons from | |
How can complex mechanisms | |
How can one reason with imprecise concepts? 115 | |
Other editions - View all
Probably Approximately Correct: Nature's Algorithms for Learning and ... Leslie Valiant Limited preview - 2013 |
Probably Approximately Correct: Nature's Algorithms for Learning and ... Leslie Valiant No preview available - 2013 |
Probably Approximately Correct: Nature's Algorithms for Learning and ... Leslie Valiant No preview available - 2014 |
Common terms and phrases
achieve Alan Turing animals artificial intelligence assumptions behavior biology Boolean Boolean function brain Chapter circuits cognition complex computer science concepts conjunctions criterion cryptography currently Darwin defined described disjunctions distribution Earth ecorithms environment error evolutionary evolutionary algorithm evolvable exist experiences exponential expression formulation genome Halting Problem human hypothesis ideal function individuals induction input knowledge known L. G. Valiant labeled Learnable Regularity learnable target learner learning algorithms light bulbs limited linear loss function machine learning marble types mathematical mechanisms mind’s eye natural notion NP-complete number of examples organisms PAC learnable PAC learning particular perceptron algorithm performance phenomenon physical polynomial possible predictions problem protein quantitative quantum question random result rithm robust logic scene sense sequence simple species statistical target pursuit task theoryless tion Turing machine Turing Test Turing’s understand unsupervised learning variables variants words