Virtual sample generation using a population of networks

Authors:
Sungzoon Cho;Min Jang;Sungjune Chang
Affiliations:
Department of Computer Science and Engineering, Information Research Laboratories, Pohang University of Science and Technology, Pohang, Kyungbuk, 790–784, Korea. E-mail: zoon@postech.ac.kr;Department of Computer Science and Engineering, Information Research Laboratories, Pohang University of Science and Technology, Pohang, Kyungbuk, 790–784, Korea. E-mail: zoon@postech.ac.kr;Department of Computer Science and Engineering, Information Research Laboratories, Pohang University of Science and Technology, Pohang, Kyungbuk, 790–784, Korea. E-mail: zoon@postech.ac.kr
Venue:
Neural Processing Letters
Year:
1997

Citing 4
Cited 3

On the approximate realization of continuous mappings by neural networks

Neural Networks
Hints

Neural Computation
The effects of adding noise during backpropagation training on a generalization performance

Neural Computation
Active learning with statistical models

Journal of Artificial Intelligence Research

Observational Learning with Modular Networks

IDEAL '00 Proceedings of the Second International Conference on Intelligent Data Engineering and Automated Learning, Data Mining, Financial Engineering, and Intelligent Agents
VTG schemes for using back propagation for multivariate time series prediction

Applied Soft Computing
A latent information function to extend domain attributes to improve the accuracy of small-data-set forecasting

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multilayer perceptrons have been shown to approximate any continuous functions with a desired precision.With insufficient training samples, however,the network can not learn the function properlyand popular model selection methods such as cross validation can not be used. We propose a scheme to generate virtual samplesusing a population of networks. They are applied to regressionproblems and are shown to improve generalization and to solve the model selection problem at the same time.