USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS

Authors
CHIANG CC FU HC
Citation
Cc. Chiang et Hc. Fu, USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS, IEEE transactions on neural networks, 5(3), 1994, pp. 516-519
Citations number
6
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
5
Issue
3
Year of publication
1994
Pages
516 - 519
Database
ISI
SICI code
1045-9227(1994)5:3<516:UMQSNT>2.0.ZU;2-Z
Abstract
This letter proposes a new type of neurons called multithreshold quadr atic sigmoidal neurons to improve the classification capability of mui tilayer neural networks. In cooperation with single-threshold quadrati c sigmoidal neurons, the multithreshold quadratic sigmoidal neurons ca n be used to improve the classification capability of multilayer neura l networks by a factor of four compared to committee machines and by a factor of two compared to the conventional sigmoidal multilayer perce ptrons.