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
Boosting and combination of classifiers for natural language call routing systems
TL;DR: This paper describes methods to improve a single classifier: boosting, discriminative training (DT) and automatic relevance feedback (ARF), and explores ways of deriving and combining uncorrelated classifiers in order to improve accuracy.
Journal ArticleDOI
Learning loopy graphical models with latent variables: Efficient methods and guarantees
TL;DR: In this paper, the problem of structural consistency in graphical models with latent variables is considered and conditions for tractable graph estimation are derived with provable guarantees, where the underlying Markov graph is locally tree-like, and the model is in the regime of correlation decay.
Journal ArticleDOI
A visual analytics system for multi-model comparison on clinical data predictions
TL;DR: A visual analytics system that compares multiple models' prediction criteria and evaluates their consistency is developed that can generate knowledge on different models' inner criteria and how confidently the authors can rely on each model's prediction for a certain patient.
Proceedings Article
Learning to Align Polyphonic Music.
TL;DR: This work describes an efficient learning algorithm for aligning a symbolic representation of a musical piece with its acoustic counterpart and compares its discriminative approach to a generative method based on a generalization of hidden Markov models.
Proceedings ArticleDOI
A statistical approach to rule learning
Ulrich Rückert,Stefan Kramer +1 more
TL;DR: A new, statistical approach to rule learning is presented that is competitive with existing rule learning algorithms and that its flexible learning bias can be adjusted to improve predictive accuracy considerably.