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
Book ChapterDOI
Bounds on the sample complexity for private learning and private data release
TL;DR: This work examines several private learning tasks and gives tight bounds on their sample complexity, and shows strong separations between sample complexities of proper and improper private learners (such separation does not exist for non-private learners), and between sample complications of efficient and inefficient proper private learners.
Journal ArticleDOI
Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation
TL;DR: The fuzzy lattice reasoning (FLR) classifier is presented for inducing descriptive, decision-making knowledge (rules) in a mathematical lattice data domain including space R^N, and the results compare favorably with results obtained by C4.5 decision trees, fuzzy-ART as well as back-propagation neural networks.
Journal Article
Domain-specific optimization in automata learning
TL;DR: In this paper, the authors optimize a standard learning method according to domain-specific structural properties to generate abstract models for complex reactive systems, which can provide the key towards controlling the evolution of complex systems, form the basis for test generation and may be applied as monitors for running applications.
Proceedings ArticleDOI
Learning submodular functions
TL;DR: This paper considers PAC-style learning of submodular functions in a distributional setting and uses lossless expanders to construct a new family of matroids which can take wildly varying rank values on superpolynomially many sets; no such construction was previously known.
Journal ArticleDOI
A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method
TL;DR: The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques.