Improving Generalization Ability of Self-Generating Neural Networks Through Ensemble Averaging

Authors:
Hirotaka Inoue;Hiroyuki Narihisa
Affiliations:
-;-
Venue:
PADKK '00 Proceedings of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Current Issues and New Applications
Year:
2000

Citing 2
Cited 7

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Self-Organizing Maps

Self-Organizing Maps

Optimizing a Multiple Classifier System

PRICAI '02 Proceedings of the 7th Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence
Efficient Incremental Learning Using Self-Organizing Neural Grove

Neural Information Processing
Self-Organizing Neural Grove: Efficient Multiple Classifier System with Pruned Self-Generating Neural Trees

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Self-Organizing Neural Grove and Its Parallel and Distributed Performance

ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Self-organizing neural grove: effective multiple classifier system with pruned self-generating neural trees

ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Study of neural networks for electric power load forecasting

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Self-organizing neural grove and its distributed performance

ICA3PP'10 Proceedings of the 10th international conference on Algorithms and Architectures for Parallel Processing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an ensemble averaging effect for improving the generalization capability of self-generating neural networks applied to classification problems. The results of our computational experiments show that ensemble averaging effect is 1-7% improvements in accuracy comparing with single SGNN for three benchmark problems.