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

Author:

Li, Yujian (Li, Yujian.)

Indexed by:

EI Scopus

Abstract:

The concept of monotonic value is presented to predetermine the optimal or near optimal number of hidden neurons needed in a feedforward neural network with one hidden layer. The approximation of an estimated neural network to y=sin(2πx) is weli simulated and the monotonic value of Xor is proven to be 2.

Keyword:

Graph theory Set theory Backpropagation Computer simulation Learning systems Least squares approximations Learning algorithms Feedforward neural networks Multilayer neural networks

Author Community:

  • [ 1 ] [Li, Yujian]Beijing Municipal Key Laboratory, Coll. of Comp. Sci. and Technology, Beijing University of Technology, Beijing 100022, China

Reprint Author's Address:

  • 李玉鑑

Show more details

Related Keywords:

Source :

ISSN: 0884-3627

Year: 2003

Volume: 2

Page: 1322-1326

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 6

Online/Total:491/10591865
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.