NEURAL NETWORK ENSEMBLES

被引:2721
|
作者
HANSEN, LK [1 ]
SALAMON, P [1 ]
机构
[1] SAN DIEGO STATE UNIV,DEPT MATH SCI,SAN DIEGO,CA 92182
关键词
Crossvalidation; fault tolerant computing; N-version programming; neural networks;
D O I
10.1109/34.58871
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose several means for improving the performance and training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining residual “generalization” error can be reduced by invoking ensembles of similar networks. © 1990 IEEE
引用
收藏
页码:993 / 1001
页数:9
相关论文
共 50 条
  • [1] A survey of neural network ensembles
    Zhao, Y
    Gao, J
    Yang, XZ
    PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 438 - 442
  • [2] Multistage neural network ensembles
    Yang, S
    Browne, A
    Picton, PD
    MULTIPLE CLASSIFIER SYSTEMS, 2002, 2364 : 91 - 97
  • [3] Deep Neural Network Ensembles
    Tao, Sean
    MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE, 2019, 11943 : 1 - 12
  • [4] Clustering ensembles of neural network models
    Bakker, B
    Heskes, T
    NEURAL NETWORKS, 2003, 16 (02) : 261 - 269
  • [5] Decision fusion in neural network ensembles
    Wanas, NM
    Kamel, M
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 2952 - 2957
  • [6] Visualizing Forecasts of Neural Network Ensembles
    von Metthenheim, Hans-Joerg
    Koepp, Cornelius
    Breitner, Michael H.
    OPERATIONS RESEARCH PROCEEDINGS 2011, 2012, : 573 - 578
  • [7] Global and local neural network ensembles
    Universidad Autonoma de Madrid, Madrid, Spain
    Pattern Recognit Lett, 8 (651-655):
  • [8] Bounded Learning for Neural Network Ensembles
    Liu, Yong
    Zhao, Qiangfu
    Pei, Yan
    2015 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, 2015, : 1216 - 1221
  • [9] Weighted combination of neural network ensembles
    Wanas, NM
    Kamel, MS
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1748 - 1752
  • [10] Neural Network Ensembles in Reinforcement Learning
    Fausser, Stefan
    Schwenker, Friedhelm
    NEURAL PROCESSING LETTERS, 2015, 41 (01) : 55 - 69