Probably approximately correct learning
|
Probably approximately correct learning (PAC learning) is a framework of learning that was proposed by Leslie Valiant in his paper A theory of the learnable.
In this framework the learner gets samples that are classified according to a function from a certain class. The aim of the learner is to find an approximation of the function with high probability. We demand the learner to be able to learn the concept given any arbitrary approximation ratio, probability of success or distribution of the samples.
The model was further extended to treat noise (misclassified samples). The PAC framework allowed accurate mathematical analysis of learning.
PAC learning framework is part of computational learning theory.
References
- L. Valiant. A theory of the learnable. Communications of the ACM, 27, 1984. The paper that proposed the PAC learning framework.
- M. Kearns, U. Vazirani. An Introduction to Computational Learning Theory. MIT Press, 1994. A textbook.
External link
- Probably Approximately Correct Learning (http://citeseer.ist.psu.edu/haussler90probably.html) - excellent introduction to the topic