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
Proceedings ArticleDOI
Learning with Cascade for Classification of Non-Convex Manifolds
TL;DR: It is proved that AdaBoost learning with cascade is effective when a complete or over-complete set of features (or weak classifiers) is available and leads to improved convergence and accuracy.
Proceedings Article
Toward a Theory of Learning Coherent Concepts
Dan Roth,Dmitry Zelenko +1 more
TL;DR: A theory for learning scenarios where multiple learners co-exist but there are mutual compatibility constraints on their outcomes is developed to resolve the contrast between the hardness of learning as predicted by the current theoretical models and the apparent ease at which cognitive systems seem to learn.
Book ChapterDOI
A New Approach for Active Automata Learning Based on Apartness
TL;DR: The $$L^{\#}$$ algorithm as discussed by the authors is a simple approach to active automata learning, which does not require auxiliary notions such as observation tables or discrimination trees, but operates directly on tree-shaped automata.
Journal ArticleDOI
Cryptographic verification of test coverage claims
TL;DR: In this paper, the authors explore cryptographic techniques that can be used to verify test coverage claims without forcing vendors to give up valuable technical secrets, but their techniques have certain limitations, which are discussed in this paper.
Journal ArticleDOI
Interface protocol inference to aid understanding legacy software components
Kousar Aslam,Loek Cleophas,Ramon R. H. Schiffelers,Ramon R. H. Schiffelers,Mark van den Brand +4 more
TL;DR: In this article, an approach to infer the interface protocols of software components from the behavioral models of those components, learned by a black-box technique called active automata learning is presented.