A Fault-Tolerant Optimal Interpolative Net

Daniel J. Simon; Hossny El-Sherief

doi:10.1109/ICNN.1993.298665

A Fault-Tolerant Optimal Interpolative Net

Daniel J. Simon, Hossny El-Sherief

TRW System Integration Group

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

Abstract

The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI Net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons generated during the learning procedure while maintaining the generalization capabilities of the network. The learning algorithm for the fault tolerant OI Net is presented in a recursive format, allowing for relatively short training times. A simulated fault tolerant OI Net is tested on a navigation satellite selective problem.

Original language	American English
Journal	IEEE Conference on Neural Networks
Volume	2
DOIs	https://doi.org/10.1109/ICNN.1993.298665
State	Published - Mar 1 1993

Keywords

Classification network
Fault tolerant optimal interpolative net
Recursive learning algorithm

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/ICNN.1993.298665License: CC BY

A Fault-Tolerant Optimal Interpolative NetFinal published version, 1.68 MBLicense: CC BY

Cite this

@article{b4fe5f4327304e53a753d362e723240f,

title = "A Fault-Tolerant Optimal Interpolative Net",

abstract = " The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI Net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons generated during the learning procedure while maintaining the generalization capabilities of the network. The learning algorithm for the fault tolerant OI Net is presented in a recursive format, allowing for relatively short training times. A simulated fault tolerant OI Net is tested on a navigation satellite selective problem.",

keywords = "Classification network, Fault tolerant optimal interpolative net, Recursive learning algorithm",

author = "Simon, \{Daniel J.\} and Hossny El-Sherief",

note = "D. Simon and H. El-Sherief. (1993). A Fault-Tolerant Optimal Interpolative Net. IEEE Conference on Neural Networks, 825-830, doi: 10.1109/ICNN.1993.298665.",

year = "1993",

month = mar,

day = "1",

doi = "10.1109/ICNN.1993.298665",

language = "American English",

volume = "2",

journal = "IEEE Conference on Neural Networks",

}

TY - JOUR

T1 - A Fault-Tolerant Optimal Interpolative Net

AU - Simon, Daniel J.

AU - El-Sherief, Hossny

N1 - D. Simon and H. El-Sherief. (1993). A Fault-Tolerant Optimal Interpolative Net. IEEE Conference on Neural Networks, 825-830, doi: 10.1109/ICNN.1993.298665.

PY - 1993/3/1

Y1 - 1993/3/1

N2 - The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI Net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons generated during the learning procedure while maintaining the generalization capabilities of the network. The learning algorithm for the fault tolerant OI Net is presented in a recursive format, allowing for relatively short training times. A simulated fault tolerant OI Net is tested on a navigation satellite selective problem.

AB - The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI Net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons generated during the learning procedure while maintaining the generalization capabilities of the network. The learning algorithm for the fault tolerant OI Net is presented in a recursive format, allowing for relatively short training times. A simulated fault tolerant OI Net is tested on a navigation satellite selective problem.

KW - Classification network

KW - Fault tolerant optimal interpolative net

KW - Recursive learning algorithm

UR - https://engagedscholarship.csuohio.edu/enece_facpub/173

U2 - 10.1109/ICNN.1993.298665

DO - 10.1109/ICNN.1993.298665

M3 - Article

VL - 2

JO - IEEE Conference on Neural Networks

JF - IEEE Conference on Neural Networks

ER -

A Fault-Tolerant Optimal Interpolative Net

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this