Open AccessBook
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
Reads0
Chats0
TLDR
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.Abstract:
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata by experimentation appendix - some tools for probabilistic analysis.read more
Citations
More filters
Journal ArticleDOI
The synthesis of language learners
TL;DR: The proofs of some of the positive results yield, as pleasant corollaries, subset-principle or tell-tale style characterizations for the learnability of the corresponding classes or families indexed.
Proceedings Article
Optimal Learning via the Fourier Transform for Sums of Independent Integer Random Variables
TL;DR: In this article, the authors studied the structure and learnability of sums of independent integer random variables (SIIRVs) of order n 2 Z+ and showed that the optimal sample complexity of this learning problem is (( k = 2 ) p log(1= )).
Journal ArticleDOI
Extension of the PAC framework to finite and countable Markov chains
TL;DR: For a Markov chain with finitely many states, it is shown that, if the target set belongs to a family of sets with a finite Vapnik-Chervonenkis (1995) dimension, then probably approximately correct (PAC) learning of this set is possible with polynomially large samples.
Journal ArticleDOI
Learning experiments with genetic optimization of a generalized regression neural network
TL;DR: Experiments compare hill-climbing optimization with that of a genetic algorithm, both in conjunction with a generalized regression neural network, and results consistently favor the GRNN unified with the genetic algorithm.
Journal ArticleDOI
Self-Improving Algorithms
TL;DR: This work investigates ways in which an algorithm can improve its expected performance by fine-tuning itself automatically with respect to an arbitrary, unknown input distribution, and gives self-improving algorithms for sorting and clustering.