Robustness of feedforward neural networks

Ching Tai Chiu; Kishan G Mehrotra; Chilukuri K. Mohan; Sanjay Ranka

doi:10.1109/ICNN.1993.298655

Robustness of feedforward neural networks

Ching Tai Chiu, Kishan G Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Department of Electrical Engineering & Computer Science

Research output: Chapter in Book/Entry/Poem › Conference contribution

17 Scopus citations

Abstract

Many artificial neural networks in practical use can be demonstrated not to be fault tolerant; this can result in disasters when localized errors occur in critical parts of these networks. In this paper, we develop methods for measuring the sensitivity of links and nodes of a feedforward neural network and implement a technique to ensure the development of neural networks that satisfy well-defined robustness criteria. Experimental observations indicate that performance degradation in our robust feedforward network is significantly less than a randomly trained feedforward network of the same size by an order of magnitude.

Original language	English (US)
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	783-788
Number of pages	6
Volume	1993-January
ISBN (Print)	0780309995
DOIs	https://doi.org/10.1109/ICNN.1993.298655
State	Published - 1993
Event	IEEE International Conference on Neural Networks, ICNN 1993 - San Francisco, United States Duration: Mar 28 1993 → Apr 1 1993

Other

Other	IEEE International Conference on Neural Networks, ICNN 1993
Country/Territory	United States
City	San Francisco
Period	3/28/93 → 4/1/93

ASJC Scopus subject areas

Control and Systems Engineering
Software
Artificial Intelligence

Access to Document

10.1109/ICNN.1993.298655

Cite this

Chiu, CT, Mehrotra, KG, Mohan, CK & Ranka, S 1993, Robustness of feedforward neural networks. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 1993-January, 298655, Institute of Electrical and Electronics Engineers Inc., pp. 783-788, IEEE International Conference on Neural Networks, ICNN 1993, San Francisco, United States, 3/28/93. https://doi.org/10.1109/ICNN.1993.298655

@inproceedings{b5534e8cff13481a9ca1aa7d8e7bc3f8,

title = "Robustness of feedforward neural networks",

abstract = "Many artificial neural networks in practical use can be demonstrated not to be fault tolerant; this can result in disasters when localized errors occur in critical parts of these networks. In this paper, we develop methods for measuring the sensitivity of links and nodes of a feedforward neural network and implement a technique to ensure the development of neural networks that satisfy well-defined robustness criteria. Experimental observations indicate that performance degradation in our robust feedforward network is significantly less than a randomly trained feedforward network of the same size by an order of magnitude.",

author = "Chiu, {Ching Tai} and Mehrotra, {Kishan G} and Mohan, {Chilukuri K.} and Sanjay Ranka",

year = "1993",

doi = "10.1109/ICNN.1993.298655",

language = "English (US)",

isbn = "0780309995",

volume = "1993-January",

pages = "783--788",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

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

note = "IEEE International Conference on Neural Networks, ICNN 1993 ; Conference date: 28-03-1993 Through 01-04-1993",

}

TY - GEN

T1 - Robustness of feedforward neural networks

AU - Chiu, Ching Tai

AU - Mehrotra, Kishan G

AU - Mohan, Chilukuri K.

AU - Ranka, Sanjay

PY - 1993

Y1 - 1993

N2 - Many artificial neural networks in practical use can be demonstrated not to be fault tolerant; this can result in disasters when localized errors occur in critical parts of these networks. In this paper, we develop methods for measuring the sensitivity of links and nodes of a feedforward neural network and implement a technique to ensure the development of neural networks that satisfy well-defined robustness criteria. Experimental observations indicate that performance degradation in our robust feedforward network is significantly less than a randomly trained feedforward network of the same size by an order of magnitude.

AB - Many artificial neural networks in practical use can be demonstrated not to be fault tolerant; this can result in disasters when localized errors occur in critical parts of these networks. In this paper, we develop methods for measuring the sensitivity of links and nodes of a feedforward neural network and implement a technique to ensure the development of neural networks that satisfy well-defined robustness criteria. Experimental observations indicate that performance degradation in our robust feedforward network is significantly less than a randomly trained feedforward network of the same size by an order of magnitude.

UR - http://www.scopus.com/inward/record.url?scp=84943257501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943257501&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1993.298655

DO - 10.1109/ICNN.1993.298655

M3 - Conference contribution

AN - SCOPUS:84943257501

SN - 0780309995

VL - 1993-January

SP - 783

EP - 788

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Neural Networks, ICNN 1993

Y2 - 28 March 1993 through 1 April 1993

ER -

Robustness of feedforward neural networks

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this