(Enter summary)
Abstract: We propose an active learning method with hidden-unit reduction, which is devised specially for multilayer perceptrons (MLP). First, we review our active learning method, and point out that many Fisher-information-based methods applied to MLP have a critical problem: the information matrix may be singular. To solve this problem, we derive the singularity condition of an information matrix, and propose an active learning technique that is applicable to MLP. Its effectiveness is verified through... (Update)
Cited by: More
Training Data Selection for Optimal Generalization.. - Vijayakumar.. (1998)
(Correct)
Improving Generalization Ability through Active Learning - VIJAYAKUMAR, OGAWA (1999)
(Correct)
Active Learning for Logistic Regression - Schein (2005)
(Correct)
Active bibliography (related documents): More All
0.6: Statistical Active Learning in Multilayer Perceptrons - Fukumizu (2000)
(Correct)
0.2: Learning Efficiency of Redundant Neural Networks in Bayesian.. - Watanabe (2001)
(Correct)
0.2: Algebraic Analysis for Non-identifiable Learning Machines - Watanabe (2000)
(Correct)
Similar documents based on text: More All
0.2: A Portable & Quick Japanese Parser: QJP - Kameda
(Correct)
0.2: Kernel Dimensionality Reduction for Supervised Learning - Fukumizu, Bach, Jordan
(Correct)
0.2: Kernel Dimensionality Reduction for Supervised - Learning Kenji Fukumizu (2003)
(Correct)
Related documents from co-citation: More All
21: Information-based objective functions for active data selection
- MacKay
20: Neural network exploration using optimal experiment design
- DA - 1994
12: Theory of Optimal Experiments (context) - Fedorov - 1972
BibTeX entry: (Update)
K. Fukumizu. Active learning in multilayer perceptrons. In Advances in Neural Information Processing Systems, Vol. 8, pp. 295-301. MIT Press, 1996. http://citeseer.ist.psu.edu/fukumizu96active.html More
@inproceedings{ fukumizu96active,
author = "Kenji Fukumizu",
title = "Active Learning in Multilayer Perceptrons",
booktitle = "Advances in Neural Information Processing Systems",
volume = "8",
publisher = "The {MIT} Press",
editor = "David S. Touretzky and Michael C. Mozer and Michael E. Hasselmo",
pages = "295--301",
year = "1996",
url = "citeseer.ist.psu.edu/fukumizu96active.html" }
Citations (may not include all citations):
240
Advances in Neural Information Processing Systems (context) - Cowan - 1972
99
Learning in artificial neural networks: A statistical perspe.. (context) - White - 1989
77
Neural network exploration using optimal experiment design
- Cohn - 1994 ACM DBLP
50
Optimal Design of Experiments (context) - Pukelsheim - 1993
10
A Regularity Condition of the Information Matrix of a Multil..
- Fukumizu - 1996 ACM
6
the problem of applying AIC to determine the structure of a .. (context) - Hagiwara, Toda et al. - 1993
2
Error Estimation and Learning Data Arrangement for Neural Ne.. (context) - Fukumizu, Watanabe - 1994
1
Information-based objective functions for active data select.. (context) - Conf, MacKay - 1992 ACM
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://signal.kuamp.kyoto-u.ac.jp/~kazushi/techrep.htm): More
Of Expressions; It Means That the Convolution Product - May Be
(Correct)
On the Convergence of Stochastic Iterative Dynamic.. - Jaakkola, Jordan, Singh (1993)
(Correct)
Synchronization and Desynchronization in a Network of Locally .. - Campbell, Wang (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