See this document in CiteSeerX!

Incremental Active Learning with Bias Reduction (1999)  (Make Corrections)  
Masashi Sugiyama, Hidemitsu Ogawa



  Home/Search   Context   Related

 
View or download:
ogawawww.cs.titech.a...IJCNN2000.ps.gz
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  ogawawww.cs.titec...publications (more)
(Enter author homepages)

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

Abstract: The problem of designing input signals for optimal generalization in supervised learning is called active learning. In many active learning methods devised so far, the bias of the learning results is assumed to be zero. In this paper, we remove this assumption and propose a new active learning method with the bias reduction. The e#ectiveness of the proposed method is demonstrated through computer simulations. 1 Introduction Supervised learning is obtaining an underlying rule from sampled... (Update)

Similar documents (at the sentence level):
35.7%:   Incremental Active Learning in. . . - Sugiyama, al.   (Correct)
22.7%:   Incremental Active Learning for Optimal Generalization - Sugiyama, Ogawa   (Correct)
11.3%:   Neural Computation, vol.12, no.12, pp.2909--2940, 2000. .. - For Optimal.. (2000)   (Correct)

Active bibliography (related documents):   More   All
0.6:   Incremental Projection Learning for Optimal Generalization - Sugiyama, Ogawa (2000)   (Correct)
0.5:   Incremental Construction of Projection Generalizing Neural.. - Sugiyama, Ogawa (2002)   (Correct)
0.4:   Properties of Incremental Projection Learning - Sugiyama, Ogawa (2000)   (Correct)

Similar documents based on text:   More   All
0.5:   Training Data Selection for Optimal Generalization in.. - Sugiyama, Ogawa (2000)   (Correct)
0.5:   Active Learning for Optimal Generalization - Sugiyama, Ogawa   (Correct)
0.4:   Release from Active Learning/Model Selection Dilemma.. - Sugiyama, Ogawa (2002)   (Correct)

BibTeX entry:   (Update)

@misc{ sugiyama-incremental,
  author = "Masashi Sugiyama and Hidemitsu Ogawa",
  title = "Incremental Active Learning with Bias Reduction",
  url = "citeseer.ist.psu.edu/sugiyama99incremental.html" }
Citations (may not include all citations):
132   Theory of optimal experiments (context) - Fedorov - 1972
105   Information-based objective functions for active data select.. - MacKay - 1992
77   Neural network exploration using optimal experiment design - Cohn - 1994
24   Active learning in multilayer perceptrons - Fukumizu - 1996
16   Projection filter regularization of ill-conditioned problem (context) - Ogawa - 1987
11   Neural network learning (context) - Ogawa - 1992
5   Training data selection for optimal generalization in trigon.. - Sugiyama, Ogawa
5   Incremental projection learning for optimal generalization - Sugiyama, Ogawa
5   Functional analytic approach to model selection --- Subspace.. - Sugiyama, Ogawa - 1999
4   Properties of incremental projection learning - Sugiyama, Ogawa
3   Exact incremental projection learning in the presence of noi.. (context) - Sugiyama, Ogawa

Documents on the same site (http://ogawa-www.cs.titech.ac.jp/~sugi/publications.html):   More
Pseudo Orthogonal Bases Give the Optimal Solution to Active.. - Sugiyama, Ogawa (1999)   (Correct)
Active Learning for Optimal Generalization - Sugiyama, Ogawa   (Correct)
Incremental Active Learning in. . . - Sugiyama, al.   (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