Paul W. Goldberg  Home/Search
Context
Related
| dcs.warwick.ac.uk/peop...pacunsup.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: dcs.warwick.ac.uk/...publications (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: In this paper we introduce a new framework for studying PAC learning problems, that has practical as well as theoretical motivations. In our framework the training examples are divided into the two sets associated with the two possible output labels, and each set is sent to a separate (unsupervised) learner. The two learners must independently t probability distributions to their examples, and afterwards these distributions are combined to form a hypothesis by labeling test data according ... (Update)
Similar documents (at the sentence level):
59.6%: When Can Two Unsupervised Learners Achieve PAC Separation? - Goldberg (Correct)
Active bibliography (related documents): More All
0.6: Journal of Machine Learning Research 7 (2006) 283--306.. - Paul Goldberg Pwg (Correct)
0.3: SUPPLEMENTARY INFORMATION Multi-class Cancer Diagnosis.. - Http Www-Genome Wi (Correct)
0.2: Linear Concepts and Hidden Variables - Grove, Roth (2000) (Correct)
Similar documents based on text: More All
0.0: What is the Minimum Length of a Non-Extendable Lace? - Kemnitz, Soltan (Correct)
0.0: Regression with Input-dependent Noise: A Gaussian Process.. - Goldberg, al. (1998) (Correct)
0.0: Estimating a Boolean Perceptron from its Average Satisfying.. - Goldberg (Correct)
BibTeX entry: (Update)
@inproceedings{ goldberg01when,
author = "Paul W. Goldberg",
title = "When Can Two Unsupervised Learners Achieve {PAC} Separation?",
booktitle = "14th Annual Conference on Computational Learning Theory, {COLT} 2001 and 5th {E}uropean Conference on Computational Learning Theory, {EuroCOLT} 2001, Amsterdam, The Netherlands, July 2001, Proceedings",
volume = "2111",
publisher = "Springer, Berlin",
pages = "303--319",
year = "2001",
url = "citeseer.ist.psu.edu/article/goldberg00when.html" }
Citations (may not include all citations):537 A Theory of the Learnable (context) - Valiant - 1984
465 Learnability and the Vapnik-Chervonenkis Dimension (context) - Blumer, Ehrenfeucht et al. - 1989
97 Computational Learning Theory (context) - Anthony, Biggs - 1992
84 Learning disjunctions of conjunctions (context) - Valiant - 1985
81 Equivalence of Models for Polynomial Learnability (context) - Haussler, Kearns et al. - 1991
57 the Learnability of Discrete Distributions (context) - Kearns, Mansour et al. - 1994
32 Learning mixtures of Gaussians (context) - Dasgupta - 1999
27 Learning Integer Lattices (context) - Helmbold, Sloan et al. - 1992
18 Ecient Noise-Tolerant Learning From Statistical Queries (context) - Kearns - 1993
18 Evolutionary Trees can be Learned in Polynomial Time in the .. - Cryan, Goldberg et al. - 1998
15 NoiseTolerant Distribution-Free Learning of General Geometri.. - Bshouty, Goldman et al. - 1998
12 Exact learning of discretized geometric concepts - Bshouty, Goldberg et al. - 1999
11 Ecient Distribution-free Learning of Probabilistic Concepts (context) - Kearns, Schapire - 1994
8 Large Margin DAGs for Multiclass Classication (context) - Platt, Cristianini et al. - 2000
8 Estimating a mixture of two product distributions - Freund, Mansour - 1999
3 Learning Linear Transformations - Frieze, Jerrum et al. - 1996
3 Multiclass Learning (context) - Guruswami, Sahai - 1999
Documents on the same site (http://www.dcs.warwick.ac.uk/people/academic/Paul.Goldberg/publications.html): More
Exact Learning of Discretized Geometric Concepts - Bshouty, Goldberg, Goldman.. (1998) (Correct)
Regression with Input-dependent Noise: A Gaussian Process.. - Goldberg, al. (1998) (Correct)
Learning Fixed-dimension Linear Thresholds From Fragmented Data - Goldberg (1999) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC