A node pruning algorithm based on optimal brain surgeon for feedforward neural networks

被引：0
|
作者：
Xu, Jinhua [1 ]
Ho, Daniel W. C.
机构：
[1] E China Normal Univ, Dept Comp Sci, Shanghai, Peoples R China
[2] City Univ Hong Kong, Dept Math, Hong Kong, Hong Kong, Peoples R China
来源：
ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1 | 2006年 / 3971卷
关键词：
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：
In this paper, a node pruning algorithm based on optimal brain surgeon is proposed for feedforward neural networks. First, the neural network is trained to an acceptable solution using the standard training algorithm. After the training process, the orthogonal factorization is applied to the output of the nodes in the same hidden layer to identify and prune the dependant nodes. Then, a unit-based optimal brain surgeon(UB-OBS) pruning algorithm is proposed to prune the insensitive hidden units to further reduce the size of the neural network, and no retraining is needed. Simulations are presented to demonstrate the effectiveness of the proposed approach.
引用
收藏
页码：524 / 529
页数：6
相关论文
共 50 条
  • [1] An iterative pruning algorithm for feedforward neural networks
    Castellano, G
    Fanelli, AM
    Pelillo, M
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (03): : 519 - 531
  • [2] Optimal pruning of feedforward neural networks based upon the Schmidt procedure
    Maldonado, FJ
    Manry, MT
    [J]. THIRTY-SIXTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS - CONFERENCE RECORD, VOLS 1 AND 2, CONFERENCE RECORD, 2002, : 1024 - 1028
  • [3] A sensitivity analysis algorithm for pruning feedforward neural networks
    Engelbrecht, AP
    Cloete, I
    [J]. ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 1274 - 1278
  • [4] Training Feedforward Neural Networks by Pruning Algorithm Based on Grey Incidence Analysis
    Xiong, Yan
    Wang, Li
    Li, Dawei
    [J]. 2008 INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION, VOL III, PROCEEDINGS, 2008, : 535 - 539
  • [5] A Novel Pruning Algorithm for Smoothing Feedforward Neural Networks Based on Group Lasso Method
    Wang, Jian
    Xu, Chen
    Yang, Xifeng
    Zurada, Jacek M.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (05) : 2012 - 2024
  • [6] Pruning Deep Neural Networks by Optimal Brain Damage
    Liu, Chao
    Zhang, Zhiyong
    Wang, Dong
    [J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 1092 - 1095
  • [7] Optimal brain surgeon for general dynamic neural networks
    Endisch, Christian
    Hackl, Christoph
    Schroeder, Dierk
    [J]. PROGRESS IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2007, 4874 : 15 - 28
  • [8] The optimal brain surgeon for pruning neural network architecture applied to multivariate calibration
    Poppi, RJ
    Massart, DL
    [J]. ANALYTICA CHIMICA ACTA, 1998, 375 (1-2) : 187 - 195
  • [9] An Optimal PID Control Algorithm for Training Feedforward Neural Networks
    Jing, Xingjian
    Cheng, Li
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2013, 60 (06) : 2273 - 2283
  • [10] Feedforward neural networks training with optimal bounded ellipsoid algorithm
    Rubio Avila, Jose De Jesus
    Ramirez, Andres Ferreyra
    Aviles-Cruz, Carlos
    [J]. PROCEEDINGS OF THE 9TH WSEAS INTERNATIONAL CONFERENCE ON NEURAL NETWORKS (NN' 08): ADVANCED TOPICS ON NEURAL NETWORKS, 2008, : 174 - 180
12345