Computation of Adalines' sensitivity to weight perturbation

Xiaoqin Zeng; Yingfeng Wang; Kang Zhang

doi:10.1109/TNN.2005.863418

Computation of Adalines' sensitivity to weight perturbation

Xiaoqin Zeng^*, Yingfeng Wang, Kang Zhang

^*Corresponding author for this work

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

25 Citations (Scopus)

Abstract

In this paper, the sensitivity of Adalines to weight perturbation is discussed. According to the discrete feature of Adalines' input and output, the sensitivity is defined as the probability of an Adaline's erroneous outputs due to weight perturbation with respect to all possible inputs. By means of hypercube model and analytical geometry method, a heuristic algorithm is given to accurately compute the sensitivity. The accuracy of the algorithm is verified by computer simulations.

Original language	English
Pages (from-to)	515-519
Number of pages	5
Journal	IEEE Transactions on Neural Networks
Volume	17
Issue number	2
DOIs	https://doi.org/10.1109/TNN.2005.863418
Publication status	Published - Mar 2006
Externally published	Yes

Keywords

Adaline
Madaline
Neural networks
Sensitivity

Access to Document

10.1109/TNN.2005.863418

Cite this

@article{4b28a8660b5a4003ad9f8461e64afa55,

title = "Computation of Adalines' sensitivity to weight perturbation",

abstract = "In this paper, the sensitivity of Adalines to weight perturbation is discussed. According to the discrete feature of Adalines' input and output, the sensitivity is defined as the probability of an Adaline's erroneous outputs due to weight perturbation with respect to all possible inputs. By means of hypercube model and analytical geometry method, a heuristic algorithm is given to accurately compute the sensitivity. The accuracy of the algorithm is verified by computer simulations.",

keywords = "Adaline, Madaline, Neural networks, Sensitivity",

author = "Xiaoqin Zeng and Yingfeng Wang and Kang Zhang",

year = "2006",

month = mar,

doi = "10.1109/TNN.2005.863418",

language = "English",

volume = "17",

pages = "515--519",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Computation of Adalines' sensitivity to weight perturbation

AU - Zeng, Xiaoqin

AU - Wang, Yingfeng

AU - Zhang, Kang

PY - 2006/3

Y1 - 2006/3

N2 - In this paper, the sensitivity of Adalines to weight perturbation is discussed. According to the discrete feature of Adalines' input and output, the sensitivity is defined as the probability of an Adaline's erroneous outputs due to weight perturbation with respect to all possible inputs. By means of hypercube model and analytical geometry method, a heuristic algorithm is given to accurately compute the sensitivity. The accuracy of the algorithm is verified by computer simulations.

AB - In this paper, the sensitivity of Adalines to weight perturbation is discussed. According to the discrete feature of Adalines' input and output, the sensitivity is defined as the probability of an Adaline's erroneous outputs due to weight perturbation with respect to all possible inputs. By means of hypercube model and analytical geometry method, a heuristic algorithm is given to accurately compute the sensitivity. The accuracy of the algorithm is verified by computer simulations.

KW - Adaline

KW - Madaline

KW - Neural networks

KW - Sensitivity

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000236361500020

UR - https://www.scopus.com/pages/publications/33644924034

U2 - 10.1109/TNN.2005.863418

DO - 10.1109/TNN.2005.863418

M3 - Journal Article

C2 - 16566477

SN - 1045-9227

VL - 17

SP - 515

EP - 519

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 2

ER -

Computation of Adalines' sensitivity to weight perturbation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this