Design of Extreme Learning Machine with Smoothedl0Regularization

被引：3
|
作者：
Yang, Cuili [1 ]
Nie, Kaizhe [1 ]
Qiao, Junfei [1 ]
Li, Bing [2 ]
机构：
[1] Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
[2] Wuhan Univ Technol, Sch Econ, Wuhan 430070, Peoples R China
来源：
MOBILE NETWORKS & APPLICATIONS | 2020年 / 25卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Extreme learning machine; Sparsity; l(0)regularization; Network compactness; REGULARIZATION; LARS; ELM;
D O I：
10.1007/s11036-020-01587-3
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
In extreme learning machine (ELM), a large number of hidden nodes are required due to the randomly generated hidden layer. To improve network compactness, the ELM with smoothedl(0)regularizer (ELM-SL0 for short) is studied in this paper. Firstly, thel(0)regularization penalty term is introduced into the conventional error function, such that the unimportant output weights are gradually forced to zeros. Secondly, the batch gradient method and the smoothedl(0)regularizer are combined for training and pruning ELM. Furthermore, both the weak convergence and strong convergence of ELM-SL0 are investigated. Compared with other existing ELMs, the proposed algorithm obtains better performance in terms of estimation accuracy and network sparsity.
引用
收藏
页码：2434 / 2446
页数：13
相关论文
共 50 条
  • [31] Homogeneous ensemble extreme learning machine autoencoder with mutual representation learning and manifold regularization for medical datasets
    Wenjian Chen
    Xiaoyun Chen
    Yanming Lin
    Applied Intelligence, 2023, 53 : 15476 - 15495
  • [32] WR-ELM: Weighted Regularization Extreme Learning Machine for Imbalance Learning in Software Fault Prediction
    Bal, Pravas Ranjan
    Kumar, Sandeep
    IEEE TRANSACTIONS ON RELIABILITY, 2020, 69 (04) : 1355 - 1375
  • [33] Random Fourier extreme learning machine with l2,1-norm regularization
    Zhou, Sihang
    Liu, Xinwang
    Liu, Qiang
    Wang, Siqi
    Zhu, Chengzhang
    Yin, Jianping
    NEUROCOMPUTING, 2016, 174 : 143 - 153
  • [34] Homogeneous ensemble extreme learning machine autoencoder with mutual representation learning and manifold regularization for medical datasets
    Chen, Wenjian
    Chen, Xiaoyun
    Lin, Yanming
    APPLIED INTELLIGENCE, 2023, 53 (12) : 15476 - 15495
  • [35] Extreme Learning Regression for nu Regularization
    Ding, Xiao-Jian
    Yang, Fan
    Liu, Jian
    Cao, Jie
    APPLIED ARTIFICIAL INTELLIGENCE, 2020, 34 (05) : 378 - 395
  • [36] Design and Validation of Reversing Assistant Based on Extreme Learning Machine
    Di, Huanyu
    Yan, Yipeng
    Zhao, Mingxin
    Kang, Mingxin
    FRONTIERS IN ENERGY RESEARCH, 2022, 10
  • [37] Efficient Inverse Extreme Learning Machine for Parametric Design of Metasurfaces
    Xiao, Li-Ye
    Jin, Fu-Long
    Wang, Bing-Zhong
    Liu, Qing Huo
    Shao, Wei
    IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS, 2020, 19 (06): : 992 - 996
  • [38] Direct Heuristic Dynamic Programming Design with Extreme Learning Machine
    Luo, Xiong
    Lv, Yixuan
    Wang, Weiping
    Zhou, Mi
    Zhao, Wenbing
    2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 1961 - 1967
  • [39] Efficient Extreme Learning Machine with Transfer Functions for Filter Design
    Xiao, Li-Ye
    Shao, Wei
    Liang, Tu-Lu
    Wang, Bing-Zhong
    2017 IEEE MTT-S INTERNATIONAL MICROWAVE SYMPOSIUM (IMS), 2017, : 551 - 553
  • [40] Short-term load forecasting based on improved manifold regularization extreme learning machine
    Li D.
    Yan Z.
    Yao L.
    Zheng H.
    Yan, Zhenlin (2014yzl@sina.com), 2016, Science Press (42): : 2092 - 2099
12345