(Enter summary)
Abstract: A constructive learning algorithm is described
that builds a feedforward neural network with an optimal
number of hidden units to balance convergence and generalization.
The method starts with a small training set and a
small network, and expands the training set incrementally
after training. If the training does not converge, the network
grows incrementally to increase its learning capacity.
This process, called selective learning with flexible neural
architectures (self), results in a... (Update)
Context of citations to this paper: More
.... the connection would disappear unless reinforced [20] Selective Learning with Flexible Neural Architectures (SELF) was introduced by [47]. It works on both the data and the network structure. Starting with a small training set and a small feed forward network, the training...
Cited by: More
Issues of Neurodevelopment in Biological and Artificial Neural.. - Chalup (2001)
(Correct)
Learn++: An Incremental Learning Algorithm for.. - Polikar, Udpa, Udpa.. (2001)
(Correct)
Properties of Incremental Projection Learning - Sugiyama, Ogawa (2001)
(Correct)
Active bibliography (related documents): More All
2.3: An Incremental Learning Algorithm That Optimizes Network Size and.. - Zhang (1994)
(Correct)
0.5: Accelerated Learning By Active Example Selection - Zhang (1994)
(Correct)
0.4: Evolving Optimal Neural Networks Using Genetic Algorithms.. - Zhang, Mühlenbein (1993)
(Correct)
Similar documents based on text: More All
0.1: NACST/Seq: A Sequence Design System with Multiobjective.. - Kim, Shin, Lee, Zhang
(Correct)
0.0: Mathematical Analysis of Evolutionary Algorithms for.. - Mühlenbein, Mahnig
(Correct)
0.0: Comparing the adaptive Boltzmann selection schedule SDS to.. - Mahnig, Mühlenbein
(Correct)
Related documents from co-citation: More All
7: A resource-allocating network for function interpolation (context) - Platt - 1991
6: A function estimation approach to sequential learning with neural networks (context) - Kadirkamanathan, Niranjan - 1992
5: A new scheme for incremental learning
- Jutten, Chentouf - 1995
BibTeX entry: (Update)
Zhang,B. T. \An incremental learning algorithm that optimizes network size and sample size in one trial", Proc. of ICNN'94(Orlando, Florida), pp.215-220, (June 28 - July 2, 1994) . http://citeseer.ist.psu.edu/article/zhang94incremental.html More
@misc{ zhang94incremental,
author = "B. Zhang",
title = "An incremental learning algorithm that optimizes network size and sample
size in one trial",
text = "Zhang,B. T. \An incremental learning algorithm that optimizes network size
and sample size in one trial, Proc. of ICNN'94(Orlando, Florida), pp.215-220,
(June 28 - July 2, 1994) .",
year = "1994",
url = "citeseer.ist.psu.edu/article/zhang94incremental.html" }
Citations (may not include all citations):
1491
Learning internal representations by error propagation (context) - Rumelhart, Hinton et al. - 1986
623
Multilayer feedforward networks are universal approximators (context) - Hornik, Stinchcombe et al. - 1989
422
Networks for approximation and learning (context) - Poggio, Girosi - 1990
372
The cascade-correlation learning architecture
- Fahlman, Lebiere - 1990
203
What size net gives valid generalization (context) - Baum, Haussler - 1989
135
Neural networks and the bias/variance dilemma (context) - Geman, Bienenstock et al. - 1992
97
First- and second-order methods for learning between steepes..
- Battiti - 1992
72
Dynamic node creation in back-propagation networks (context) - Ash - 1989
69
The condensed nearest neighbor rule (context) - Hart - 1968
56
Back-propagation algorithm which varies the number of hidden.. (context) - Hirose, Yamashita et al. - 1991
46
Selecting concise training sets from clean data (context) - Plutowski, White - 1993
37
Generalization and network design strategies (context) - LeCun - 1989
33
Principles of risk minimization for learning theory (context) - Vapnik - 1992
32
Query-based learning applied to partially trained multilayer.. (context) - Hwang - 1991
21
Large automatic learning, rule extraction, and generalizatio.. (context) - Denker - 1987
20
Four types of learning curves
- Amari, Fujita et al. - 1992
19
Accelerated learning by active example selection
- Zhang - 1993
15
Neural network constructive algorithms: Trading generalizati..
- 'Smieja - 1993
13
Neural networks that teach themselves through genetic discov.. (context) - Zhang, Veenker - 1991
12
Scaling and generalization in neural networks: a case study (context) - Ahmad, Tesauro - 1988
10
Learning by Genetic Neural Evolution (context) - Zhang - 1992
8
Focused incremental learning for improved generalization wit.. (context) - Zhang, Veenker - 1991
6
The Vapnik-Chervonenkis dimension: information versus comple.. (context) - Abu-Mostafa - 1989
5
Self-development learning: Constructing optimal size neural .. (context) - Zhang - 1993
4
the approximate realization of continuous mappingsby neural .. (context) - Funahashi - 1989
4
Learning and using specific instances (context) - Volper, Hampson - 1987
3
Generalization in connectionist networks that realize Boolea.. (context) - Huyser, Horowitz - 1988
3
Constructive learning by specialization (context) - Refenes, Vithlani - 1991
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.ais.fraunhofer.de/~muehlen/pegasus/publications.html): More
The Factorized Distribution Algorithm for Additively.. - Mühlenbein, Mahnig (1999)
(Correct)
On the Mean Convergence Time of Evolutionary Algorithms.. - Asoh, Mühlenbein (1994)
(Correct)
Evolution in Time and Space - The Parallel Genetic Algorithm - Mühlenbein (1991)
(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