Bounds on number of hidden neurons of multilayer perceptrons…

Established

14
Citations
14
Refs
2002
Year
Search Works
Work Details
  • DOI 10.1109/iscas.1990.112518
  • OpenAlex ID W1949720511
  • Type Conference-paper
  • Language EN
  • Published 04 Dec 2002
  • Volume 1
  • Pages 2500–2503
  • Source IEEE International Symposium on Circuits…
  • FWCI 0.27
  • Countries 1
  • Institutions 1
  • Added 24 Jun 2016
  • Updated 06 Oct 2026
External Links
OpenAlex Record DOI Resolver
MENU
0

Bounds on number of hidden neurons of multilayer perceptrons in classification and recognition

Conference-paper 2002 EN

The use of multilayer perceptrons (MLP) in the realization of arbitrary functions which map from a finite subset of E/sup n/ into E/sup m/ is investigated. A least upper bound of hidden neurons needed to solve this problem is derived. It is shown that as long as the number of hidden neurons exceeds this bound, an MLP can realize arbitrary switching functions without requiring learning algorithms.…

14

Citations

14

References

2

Authors

0.27

FWCI

Citations by Year
Last 5 years
Topics
Keywords
Authors & Affiliations
2 authors
#AuthorInstitutionsORCID
1 S.C. Huang University of Notre Dame (US)
2 Yih-Fang Huang University of Notre Dame (US)
Related Works
10

Data: OpenAlex