• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Sun, Y.-F. (Sun, Y.-F..) (Scholars:孙艳丰) | Yang, X.-D. (Yang, X.-D..) (Scholars:杨晓东) | Hu, Y.-L. (Hu, Y.-L..) (Scholars:胡永利) | Wang, P. (Wang, P..)

Indexed by:

Scopus PKU CSCD

Abstract:

In the extreme learning machine (ELM) network, sigmoid activation function is usually chosen for additive hidden neurons. Therefore, this paper replaced this activation function with a smooth approximation called softplus function. Because of being closer to the biological activation model and having certain sparseness, softplus activation function can further optimize network performance. In order to have a better classification performance, the optimization model of ELM by the improved Fisher discriminative analysis was restricted, and animproved ELM algorithm was proposed. Thus the output weights can be obtained analytically and are more conducive for classification. Finally, the experiments on handwritten digit database and face database prove the feasibility and superiority of the improved ELM algorithm. ©, 2015, Beijing University of Technology. All right reserved.

Keyword:

Activation function; ELM algorithm; Fisher discrimination

Author Community:

  • [ 1 ] [Sun, Y.-F.]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, College of Metropolitan Transportation, Beijing University of Technology, Beijing, 100124, China
  • [ 2 ] [Yang, X.-D.]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, College of Metropolitan Transportation, Beijing University of Technology, Beijing, 100124, China
  • [ 3 ] [Hu, Y.-L.]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, College of Metropolitan Transportation, Beijing University of Technology, Beijing, 100124, China
  • [ 4 ] [Wang, P.]College of Applied Science, Harbin University of Science and Technology, Harbin, 150080, China

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Related Article:

Source :

Journal of Beijing University of Technology

ISSN: 0254-0037

Year: 2015

Issue: 9

Volume: 41

Page: 1341-1348

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 7

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 0

Online/Total:443/5439947
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.