See this document in CiteSeerX!

Improving Generalization with Active Learning (1992)  (Make Corrections)  (91 citations)
David Cohn, Les Atlas, et al.
Machine Learning



  Home/Search   Context   Related

Links:   ACM   DBLP

 
View or download:
mit.edu/people/cohn/...selsampling.ps.Z
cmu.edu/~cohn/psyche...selsampling.ps.Z
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  mit.edu/people/cohn/papers (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: Active learning differs from passive "learning from examples" in that the learning algorithm assumes at least some control over what part of the input domain it receives information about. In some situations, active learning is provably more powerful that learning from examples alone, giving better generalization for a fixed number of training examples. In this paper, we consider the problem of learning a binary concept in the absence of noise (Valiant 1984). We describe a formalism for active... (Update)

Cited by:   More
Active Learning with Multiple Views - Muslea (2002)   (Correct)
Coarse Sample Complexity Bounds for Active - Learning Sanjoy Dasgupta   (Correct)
Text Classification for Intelligent - Portfolio Management Young-Woo (2002)   (Correct)

Similar documents (at the sentence level):
44.9%:   Separating Formal Bounds from Practical Performance in Learning.. - Cohn (1992)   (Correct)

Active bibliography (related documents):   More   All
0.3:   Towards Static-Security Assessment of a Large-Scale.. - Weerasooriya.. (1992)   (Correct)
0.2:   Neural Network Exploration Using Optimal Experiment Design - Cohn (1994)   (Correct)
0.2:   Improving Generalization Ability through Active Learning - VIJAYAKUMAR, OGAWA (1999)   (Correct)

Similar documents based on text:   More   All
0.1:   Qualitative Spatial Representation and Reasoning with.. - Cohn, Bennett.. (1997)   (Correct)
0.1:   A Theory of Spatial Regions with Indeterminate Boundaries - Cohn, Gotts   (Correct)
0.1:   Spatial Regions with Undetermined Boundaries - Cohn, Gotts   (Correct)

Related documents from co-citation:   More   All
23:   Committee-based sampling for training probabilistic classifiers - Dagan, Engelson - 1995
20:   Heterogeneous uncertainty sampling for supervised learning - Lewis, Catlett - 1994
19:   Query by committee - Seung, Opper et al. - 1992

BibTeX entry:   (Update)

Cohn, D.; Atlas, L.; and Ladner, R. 1994. Improving generalization with active learning. Machine Learning 15. http://citeseer.ist.psu.edu/cohn92improving.html   More

@article{ cohn94improving,
    author = "David A. Cohn and Les Atlas and Richard E. Ladner",
    title = "Improving Generalization with Active Learning",
    journal = "Machine Learning",
    volume = "15",
    number = "2",
    pages = "201-221",
    year = "1994",
    url = "citeseer.ist.psu.edu/cohn92improving.html" }
Citations (may not include all citations):
1491   Learning internal representations by error propagation (context) - Rumelhart, Hinton et al. - 1986  ACM
550   Parallel Distributed Processing (context) - Rumelhart, McClelland - 1992  ACM
537   A theory of the learnable (context) - Valiant - 1984
465   Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989  ACM   DBLP
274   Generalization as search (context) - Mitchell - 1982  DBLP
244   Learning regular sets from queries and counter-examples (context) - Angluin - 1986
240   Advances in Neural Information Processing Systems (context) - Touretzky - 1992
240   Advances in Neural Information Processing Systems (context) - Hanson - 1987
203   What size net gives valid generalization (context) - Baum, Haussler - 1989
144   Optimal brain damage - Le Cunn, Denker et al. - 1990  ACM   DBLP
105   Information-based objective functions for active data select.. - MacKay  ACM
102   Training a 3-node neural network is NP-complete - Blum, Rivest - 1989  ACM   DBLP
72   Dynamic node creation in backpropagation networks (context) - Ash - 1989
39   Training connectionist networks with queries and selective s.. (context) - Cohn, Atlas et al. - 1990  ACM   DBLP
31   Discriminability-based transfer between neural networks In C - Pratt - 1993
23   the complexity of loading shallow neural networks (context) - Judd - 1988
20   and query by committee (context) - Freund, Seung et al. - 1993
19   the sample complexity of pac-learning using random and chose.. - Eisenberg, Rivest - 1990
18   Constructing hidden units using examples and queries (context) - Baum, Lang - 1991  ACM   DBLP
13   Generalizing the pac model for neural nets and other learnin.. (context) - Haussler - 1989
5   Acoustic Determinants of Infant Preference for Motherese Spe.. (context) - Fernald, Kuhl - 1987
5   Query learning based on boundary search and gradient computa.. - Hwang, Choi et al. - 1990
3   Artificial neural networks for power system static security .. (context) - Aggoune, Atlas et al. - 1989



The graph only includes citing articles where the year of publication is known.


Documents on the same site (http://www.ai.mit.edu/people/cohn/papers.html):   More
Separating Formal Bounds from Practical Performance in Learning.. - Cohn (1992)   (Correct)
Minimizing Statistical Bias with Queries - Cohn (1997)   (Correct)
Neural Network Exploration Using Optimal Experiment Design - Cohn (1994)   (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