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
  • [21] EVALUATION OF DIFFERENT REGULARIZATION METHODS FOR THE EXTREME LEARNING MACHINE APPLIED TO HYPERSPECTRAL IMAGES
    Haut, Juan M.
    Liu, Yi
    Paoletti, Mercedes E.
    Xu, Xiong
    Plaza, Javier
    Plaza, Antonio
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 3603 - 3606
  • [22] Learning with Similarity Functions: A Novel Design for the Extreme Learning Machine
    Bisio, Federica
    Gastaldo, Paolo
    Zunino, Rodolfo
    Gianoglio, Christian
    Ragusa, Edoardo
    PROCEEDINGS OF ELM-2015, VOL 1: THEORY, ALGORITHMS AND APPLICATIONS (I), 2016, 6 : 265 - 277
  • [23] Online Extreme Learning Machine Design for the Application of Federated Learning
    Chen, Yi-Ta
    Chuang, Yu-Chuan
    Wu, An-Yeu
    2020 2ND IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2020), 2020, : 188 - 192
  • [24] Learning with similarity functions: A novel design for the extreme learning machine
    Gastaldo, P.
    Bisio, F.
    Gianoglio, C.
    Ragusa, E.
    Zunino, R.
    NEUROCOMPUTING, 2017, 261 : 37 - 49
  • [25] Extreme Learning Machine Design for Dealing with Unrepresentative Features
    Nieto, Nicolas
    Ibarrola, Francisco J.
    Peterson, Victoria
    Rufiner, Hugo L.
    Spies, Ruben
    NEUROINFORMATICS, 2022, 20 (03) : 641 - 650
  • [26] Extreme Learning Machine Design for Dealing with Unrepresentative Features
    Nicolás Nieto
    Francisco J. Ibarrola
    Victoria Peterson
    Hugo L. Rufiner
    Ruben Spies
    Neuroinformatics, 2022, 20 : 641 - 650
  • [27] VLSI Extreme Learning Machine: A Design Space Exploration
    Yao, Enyi
    Basu, Arindam
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2017, 25 (01) : 60 - 74
  • [28] Neural architecture design based on extreme learning machine
    Bueno-Crespo, Andres
    Garcia-Laencina, Pedro J.
    Sancho-Gomez, Jose-Luis
    NEURAL NETWORKS, 2013, 48 : 19 - 24
  • [29] L21-Norm Based Loss Function and Regularization Extreme Learning Machine
    Li, Rui
    Wang, Xiaodan
    Lei, Lei
    Song, Yafei
    IEEE ACCESS, 2019, 7 (6575-6586) : 6575 - 6586
  • [30] A Hybrid Regularization Semi-Supervised Extreme Learning Machine Method and Its Application
    Lei, Yongxiang
    Cen, Lihui
    Chen, Xiaofang
    Xie, Yongfang
    IEEE ACCESS, 2019, 7 : 30102 - 30111
12345