Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons

Cheng Chin Chiang; Hsin-Chia Fu

doi:10.1109/72.286930

Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons

Cheng Chin Chiang, Hsin-Chia Fu

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of multilayer 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.

Original language	English
Pages (from-to)	516 - 519
Number of pages	4
Journal	IEEE Transactions on Neural Networks
Volume	5
Issue number	3
DOIs	https://doi.org/10.1109/72.286930
State	Published - May 1994

Access to Document

10.1109/72.286930

Fingerprint Dive into the research topics of 'Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons'. Together they form a unique fingerprint.

Cite this

@article{e5c9766a425a48ec909b7d05d79f9efe,

title = "Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons",

abstract = "This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of multilayer 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.",

author = "Chiang, {Cheng Chin} and Hsin-Chia Fu",

year = "1994",

month = may,

doi = "10.1109/72.286930",

language = "English",

volume = "5",

pages = "516 -- 519",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "3",

}

TY - JOUR

T1 - Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons

AU - Chiang, Cheng Chin

AU - Fu, Hsin-Chia

PY - 1994/5

Y1 - 1994/5

N2 - This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of multilayer 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.

AB - This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of multilayer 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.

U2 - 10.1109/72.286930

DO - 10.1109/72.286930

M3 - Article

VL - 5

SP - 516

EP - 519

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 3

ER -