Optimal feed-forward neural networks based on the combination of constructing and pruning by genetic algorithms

被引：4
|
作者：
Wang, WJ [1 ]
Lu, WZ [1 ]
Leung, AYT [1 ]
Lo, SM [1 ]
Xu, ZB [1 ]
Wang, XK [1 ]
机构：
[1] Xian Jiaotong Univ, Fac Sci, Inst Informat, Xian 710049, Peoples R China
来源：
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词：
D O I：
10.1109/IJCNN.2002.1005546
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The determination of the proper size of an artificial neural network (ANN) is recognized to be crucial, especially for its practical implementation in important issues such as learning and generalization. In this paper, an effective designing method of neural network architectures Is presented. The network is firstly trained by a dynamic constructive method until the error is satisfied. The trained network is then pruned by genetic algorithm (GA). The simulation results demonstrate the advantages in generalization and expandability of the proposed method.
引用
收藏
页码：636 / 641
页数：2
相关论文
共 50 条
  • [1] Developing optimal feed-forward neural networks using a constructive dynamic training method and pruning with a genetic algorithm
    Wang, W.
    Lu, W.
    Wang, X.
    Leung, A. Y. T.
    Proceedings of The Seventh International Conference on the Application of Artificial Intelligence to Civil and Structural Engineering, 2003, : 115 - 116
  • [2] Constructing and training feed-forward neural networks for pattern classification
    Jiang, XD
    Wah, AHKS
    PATTERN RECOGNITION, 2003, 36 (04) : 853 - 867
  • [3] Optimal identification using feed-forward neural networks
    Vergara, V
    Sinne, S
    Moraga, C
    FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 1052 - 1059
  • [4] Feed-forward neural networks
    Bebis, George
    Georgiopoulos, Michael
    IEEE Potentials, 1994, 13 (04): : 27 - 31
  • [5] Faults Diagnosis of Induction Machine by Using Feed-Forward Neural Networks and Genetic Algorithms
    Hasni, M.
    Hamdani, S.
    Taibi, Z. M.
    Touhami, O.
    Ibtiouen, R.
    Rezzoug, A.
    2013 9TH ASIAN CONTROL CONFERENCE (ASCC), 2013,
  • [6] Parallelizable Reachability Analysis Algorithms for Feed-Forward Neural Networks
    Tran, Hoang-Dung
    Musau, Patrick
    Lopez, Diego Manzanas
    Yang, Xiaodong
    Nguyen, Luan Viet
    Xiang, Weiming
    Johnson, Taylor T.
    2019 IEEE/ACM 7TH INTERNATIONAL WORKSHOP ON FORMAL METHODS IN SOFTWARE ENGINEERING (FORMALISE 2019), 2019, : 31 - 40
  • [7] A New Sensitivity-Based Pruning Technique for Feed-Forward Neural Networks That Improves Generalization
    Mrazova, Iveta
    Reitermanova, Zuzana
    2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 2143 - 2150
  • [8] Yet another genetic algorithm for feed-forward neural networks
    Neruda, R
    NINTH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1997, : 375 - 380
  • [9] A quantum model of feed-forward neural networks with unitary learning algorithms
    Changpeng Shao
    Quantum Information Processing, 2020, 19
  • [10] A quantum model of feed-forward neural networks with unitary learning algorithms
    Shao, Changpeng
    QUANTUM INFORMATION PROCESSING, 2020, 19 (03)
12345