標題: USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS
作者: CHIANG, CC
FU, HC
資訊工程學系
Department of Computer Science
公開日期: 1-May-1994
摘要: This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of muitilayer neural networks. In cooperation with single-threshold quadratic sigmoidal neurons, the multithreshold quadratic sigmoidal neurons can be used to improve the classification capability of multilayer neural networks by a factor of four compared to committee machines and by a factor of two compared to the conventional sigmoidal multilayer perceptrons.
URI: http://dx.doi.org/10.1109/72.286930
http://hdl.handle.net/11536/2498
ISSN: 1045-9227
DOI: 10.1109/72.286930
期刊: IEEE TRANSACTIONS ON NEURAL NETWORKS
Volume: 5
Issue: 3
起始頁: 516
結束頁: 519
Appears in Collections:Articles


Files in This Item:

  1. A1994NR36000024.pdf