A Pruning Algorithm for Extreme Learning Machine

被引:0
作者
Li Ying [1 ]
Li Fan-jun [2 ]
机构
[1] Qi Lu Univ Technol, Sch Sci, Jinan 250353, Shandong, Peoples R China
[2] Univ Jinan, Sch Math Sci, Jinan 250022, Shandong, Peoples R China
来源
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2013 | 2013年 / 8206卷
关键词
Single-hidden-layer feedforward neural networks; Extreme Learning Machine; Sensitivity analysis; Pruning algorithm; FEEDFORWARD NETWORKS; HIDDEN NEURONS; NUMBER;
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
It is difficult for Extreme Learning Machine (ELM) to estimate the number of hidden nodes used to match with the learning data. In this paper, a novel pruning algorithm based on sensitivity analysis is proposed for ELM. The measure to estimate the necessary number of hidden layer nodes is presented according to the defined sensitivity. When the measure is below the given threshold, the nodes with smaller sensitivities are removed from the existent network all together. Experimental results show that the proposed method can produce more compact neural network than some other existing similar algorithms.
引用
收藏
页码:1 / 7
页数:7
相关论文
共 13 条
  • [1] [Anonymous], 1989, P C ADV NEUR INF PRO
  • [2] Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning
    Feng, Guorui
    Huang, Guang-Bin
    Lin, Qingping
    Gay, Robert
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (08): : 1352 - 1357
  • [3] HASSIBI B, 1992, P IEEE INT C NEUR NE, P293
  • [4] Can threshold networks be trained directly?
    Huang, GB
    Zhu, QY
    Mao, KZ
    Siew, CK
    Saratchandran, P
    Sundararajan, N
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2006, 53 (03) : 187 - 191
  • [5] Learning capability and storage capacity of two-hidden-layer feedforward networks
    Huang, GB
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (02): : 274 - 281
  • [6] Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions
    Huang, GB
    Babri, HA
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (01): : 224 - 229
  • [7] Enhanced random search based incremental extreme learning machine
    Huang, Guang-Bin
    Chen, Lei
    [J]. NEUROCOMPUTING, 2008, 71 (16-18) : 3460 - 3468
  • [8] Extreme learning machine: Theory and applications
    Huang, Guang-Bin
    Zhu, Qin-Yu
    Siew, Chee-Kheong
    [J]. NEUROCOMPUTING, 2006, 70 (1-3) : 489 - 501
  • [9] Universal approximation using incremental constructive feedforward networks with random hidden nodes
    Huang, Guang-Bin
    Chen, Lei
    Siew, Chee-Kheong
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (04): : 879 - 892
  • [10] OP-ELM: Optimally Pruned Extreme Learning Machine
    Miche, Yoan
    Sorjamaa, Antti
    Bas, Patrick
    Simula, Olli
    Jutten, Christian
    Lendasse, Amaury
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (01): : 158 - 162