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
Complexity parameters for first order classes
Marta Arias,Roni Khardon +1 more
TL;DR: This work identifies an alternative notion of size and a simple set of parameters that are useful for first order Horn Expressions and matches lower bounds derived using the Vapnik Chervonenkis dimension complete the picture showing that these parameters are indeed crucial.
Journal Article
Universal Kernel-Based Learning with Applications to Regular Languages
TL;DR: It is proved that all concepts are linearly separable under this mapping, which presents a substantial departure from current learning paradigms and in particular yields a novel method for learning this fundamental concept class.
Posted Content
Eclectic Extraction of Propositional Rules from Neural Networks
TL;DR: Heretic as mentioned in this paper uses Inductive Decision Tree learning combined with information of the neural network structure for extracting logical rules, which is a hybrid algorithm that combines the other approaches to attain more performance.
Journal ArticleDOI
DACH: Domain Adaptation Without Domain Information
TL;DR: This article discusses the possibility of learning domain adaptations even when the data does not contain domain labels, and proposes a new model, named domain adaption using cross-domain homomorphism (DACH in short), to identify intrinsic homomorphicism hidden in mixed data from all domains.
Journal ArticleDOI
Learning to verify branching time properties
Abhay Vardhan,Mahesh Viswanathan +1 more
TL;DR: A new model checking algorithm for verifying computation tree logic (CTL) properties based on using language inference to learn the fixpoints necessary for checking a CTL formula instead of computing them iteratively as is done in traditional model checking.