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
Does Machine Learning Really Work
TL;DR: A number of recent accomplishments in machine learning are sampled and where the field might be headed is looked at.
Journal ArticleDOI
Logical settings for concept-learning
TL;DR: It is shown that learning from interpretations reduces toLearning from entailment, which in turn reduces to learning from satisfiability, which reduces to inductive logic programming and computational learning theory.
Journal ArticleDOI
Cryptographic hardness for learning intersections of halfspaces
TL;DR: The first representation-independent hardness results for PAC learning intersections of halfspaces are given, derived from two public-key cryptosystems due to Regev, which are based on the worst-case hardness of well-studied lattice problems.
Proceedings Article
Bayesian Averaging of Classifiers and the Overfitting Problem
TL;DR: This paper studies Bayesian model averaging’s application to combining rule sets, and compares it with bagging and partitioning, two popular but more ad hoc alternatives, showing its error rates are consistently higher than the other methods.
Journal ArticleDOI
Learning pattern classification-a survey
TL;DR: This basic model best illustrates intuition and analysis techniques while still containing the essential features and serving as a prototype for many applications.