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
The set covering machine with data-dependent half-spaces
TL;DR: Compared to the support vector machine, the set covering machine with data-dependent half-spaces produces substantially sparser classifiers with comparable (and sometimes better) generalization.
DissertationDOI
Adaptive processing of structural data: from sequences to trees and beyond
TL;DR: In this article, a tree-recursive dynamical system (TRDS) is proposed, which is a class of deterministic state machines that operate in a continuous state space and enable the representation and the inductive inference of structure mappings.
Journal ArticleDOI
Boosting Classifiers Built from Different Subsets of Features
TL;DR: This work proposes the decomposition of the learning task into several dependent sub-problems of boosting, treated by different weak learners, that will optimally collaborate during the weight update stage to achieve this task.
Learning and inference in phrase recognition: a filtering-ranking architecture using perceptron
TL;DR: In this article, the problem of reconeixing structures of segments in an oracio is studied, in which the goal is to find the most suitable structure for a given set of decisions.
Proceedings Article
Learning from partial observations
TL;DR: A masking process model is proposed to capture the stochastic nature of information loss and it is shown that the concept classes of parities and monotone term 1-decision lists are not properly consistently learnable from partial observations, if RP ≠ NP.