Michael Kearns And H. Sebastian Seung ,...  Home/Search
Context Related
| upenn.edu/~mkearns/papers/pop.ps.Z 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: upenn.edu/~mkearns/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents. (Update)
Context of citations to this paper: More
.... second aspect of creating an ensemble is the choice of the function for combining the predictions of the component classifiers (Kearns Seung 1995). Examples of combination functions include voting schemes (Hansen Salamon 1990) simple averages (Lincoln Skrzypek 1989)...
...biases. Researchers in computational learning theory have also analysed aspects of the area of multiple learners. These include Kearns and Seung (1995) who model the problem using an oracle . Normally, each call to the oracle returns a single classified example. They show that...
Cited by: More
Recycling Decision Trees in Numeric Domains - Kubat (Correct)
Committees Of Learning Agents - Asker, Danielson, Ekenberg (1993) (Correct)
Ensembles as a Sequence of Classifiers - Asker, Maclin (1997) (Correct)
Active bibliography (related documents): More All
0.1: Rigorous Learning Curve Bounds from Statistical Mechanics - Haussler (1996) (Correct)
0.1: Limits And Approximations For The M/g/1 Lifo Waiting-Time.. - Abate, Whitt (1997) (Correct)
0.1: Extremes on Trees - Tailen Hsing And (2002) (Correct)
Similar documents based on text: More All
0.3: Selective sampling using the Query by Committee algorithm - Freund, Seung, Shamir.. (1997) (Correct)
0.2: Permitted and Forbidden Sets in Symmetric Threshold-Linear.. - Hahnloser, Seung (Correct)
0.2: Algorithms for Non-negative Matrix Factorization - Lee, Seung (2000) (Correct)
Related documents from co-citation: More All
6: How to use expert advice (context) - Cesa-Bianchi, Freund et al. - 1993
6: A Comparative Evaluation of Voting and Meta-learning on Partitioned Data - Chan, Stolfo - 1995
6: Stacked Generalization - Wolpert - 1992
BibTeX entry: (Update)
Kearns, M. & H.S. Seung (1995), Learning from a Population of Hypotheses, Machine Learning, 18, pp. 255-276, Kluwer Academic Publishers. http://citeseer.ist.psu.edu/kearns95learning.html More
@inproceedings{ kearns93learning,
author = "Michael J. Kearns and H. Sebastian Seung",
title = "Learning from a Population of Hypotheses",
booktitle = "Computational Learing Theory",
pages = "101-110",
year = "1993",
url = "citeseer.ist.psu.edu/kearns95learning.html" }
Citations (may not include all citations):348 Estimation of Dependences Based on Empirical Data (context) - Vapnik - 1982
318 Convergence of Stochastic Processes (context) - Pollard - 1984
273 The strength of weak learnability - Schapire - 1990
268 Decision theoretic generalizations of the PAC model for neur.. (context) - Haussler - 1992
180 Boosting a weak learning algorithm by majority - Freund - 1990
85 Bounds on the sample complexity of Bayesian learning using i.. - Haussler, Kearns et al. - 1994
59 Central limit theorems for empirical measures (context) - Dudley - 1978
58 Statistical mechanics of learning from examples (context) - Seung, Sompolinsky et al. - 1992
51 How to use expert advice (context) - Cesa-Bianchi, Freund et al. - 1993
37 An improved boosting algorithm and its implications on learn.. (context) - Freund - 1992
22 A lower bound for discrimination information in terms of var.. (context) - Kullback - 1967
20 Four types of learning curves - Amari, Fujita et al. - 1992
10 Asymptotic expansions (context) - Erdelyi - 1956
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cis.upenn.edu/~mkearns/): More
Graphical Economics - Sham Kakade Michael (Correct)
Efficient Algorithms for Learning to Play Repeated Games Against.. - al. (1995) (Correct)
On the Boosting Ability of Top-Down Decision Tree Learning.. - Kearns (1996) (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