Improving generalization ability of self-generating neural networks through ensemble averaging

被引：0
|
作者：
Inoue, H [1 ]
Narihisa, H [1 ]
机构：
[1] Okayama Univ Sci, Dept Informat & Comp Engn, Okayama 7000005, Japan
来源：
KNOWLEDGE DISCOVERY AND DATA MINING, PROCEEDINGS: CURRENT ISSUES AND NEW APPLICATIONS | 2000年 / 1805卷
关键词：
self-generating neural networks; self-generating neural tree; ensemble averaging; classification; competitive learning;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：177 / 180
页数：4
相关论文
共 50 条
  • [31] ON THE ABILITY OF NEURAL NETWORKS TO PERFORM GENERALIZATION BY INDUCTION
    ANSHELEVICH, VV
    AMIRIKIAN, BR
    LUKASHIN, AV
    FRANKKAMENETSKII, MD
    BIOLOGICAL CYBERNETICS, 1989, 61 (02) : 125 - 128
  • [32] Empirical estimation of generalization ability of neural networks
    Sarkar, D.
    Neural Network World, 2001, 11 (01) : 3 - 15
  • [33] Research on Improve the Generalization Ability of Neural Network Ensemble System
    Ma, Ning
    Liao, Huihui
    Li, Bin
    SENSORS, MEASUREMENT AND INTELLIGENT MATERIALS, PTS 1-4, 2013, 303-306 : 1444 - +
  • [34] Cavitary nodule segmentation in computed tomography images based on self-generating neural networks and particle swarm optimisation
    Zhao, Juan-juan
    Ji, Guo-hua
    Xia, Yong
    Zhang, Xiao-long
    INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION, 2015, 7 (01) : 62 - 67
  • [35] Improving learning and generalization in neural networks through the acquisition of multiple related functions
    Christiansen, MH
    4TH NEURAL COMPUTATION AND PSYCHOLOGY WORKSHOP, LONDON, 9-11 APRIL 1997: CONNECTIONIST REPRESENTATIONS, 1997, : 58 - 70
  • [36] Self-Organizing Neural Grove: Efficient Multiple Classifier System with Pruned Self-Generating Neural Trees
    Inoue, Hirotaka
    ARTIFICIAL NEURAL NETWORKS - ICANN 2008, PT I, 2008, 5163 : 613 - 622
  • [37] Self-organizing neural grove: Effective multiple classifier system with pruned self-generating neural trees
    Inoue, H
    Narihisa, H
    2005 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), VOLS 1-6, CONFERENCE PROCEEDINGS, 2005, : 2502 - 2505
  • [38] Improving generalization capabilities of dynamic neural networks
    Galicki, M
    Leistritz, L
    Zwick, EB
    Witte, H
    NEURAL COMPUTATION, 2004, 16 (06) : 1253 - 1282
  • [39] Leveraging the Generalization Ability of Deep Convolutional Neural Networks for Improving Classifiers for Color Fundus Photographs
    Son, Jaemin
    Kim, Jaeyoung
    Kong, Seo Taek
    Jung, Kyu-Hwan
    APPLIED SCIENCES-BASEL, 2021, 11 (02): : 1 - 10
  • [40] Effective Neural Network Ensemble Approach for Improving Generalization Performance
    Yang, Jing
    Zeng, Xiaoqin
    Zhong, Shuiming
    Wu, Shengli
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2013, 24 (06) : 878 - 887
12345