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 Article
Distribution-independent Reliable Learning
Varun Kanade,Justin Thaler +1 more
TL;DR: The fully reliable algorithm for majorities provides the first evidence that fully reliable learning may be strictly easier than agnostic learning, and the algorithms also satisfy strong attribute-efficiency properties, and provide smooth tradeoffs between sample complexity and running time.
Proceedings Article
Piece-wise model fitting using local data patterns
TL;DR: A novel classification algorithm that fits models of different complexity on separate regions of the input space by applying a clustering algorithm to every set of training examples that belong to the same class.
Journal Article
A robust Boosting algorithm
Richard Nock,Patrice Lefaucheur +1 more
TL;DR: A new Boosting algorithm which combines the base hypotheses with symmetric functions, and is efficient even in an agnostic learning setting, and has significant resistance against noise.
Posted Content
Polynomials that Sign Represent Parity and Descartes' Rule of Signs
TL;DR: Borders on sparsity are used to derive circuit lower bounds for depth-two AND-OR-NOT circuits with a Threshold Gate at the top and exact bounds on the sparsity of such polynomials for any two element subset A are proved.
Markov models on trees: Reconstruction and applications
TL;DR: Markov Models on Trees: Reconstruction and Applications and Applications: reconstruction and applications