Neural network learning paradigms involving nonlinear spectral processing

O. K. Ersoy; D. Hong

Neural network learning paradigms involving nonlinear spectral processing

O. K. Ersoy, D. Hong

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Conference article › peer-review

3 Citations (Scopus)

Abstract

Two neural network architectures involving nonlinear spectral transformations are described. The first architecture involves generalization of nonlinear matched-filtering techniques, yielding a network that is very fast in learning and recall as well as highly accurate in classification. The second architecture is hierarchical with a number of stages; after each stage, error detection is carried out, followed by nonlinear spectral transformations when the error measure is above threshold.

Original language	English
Pages (from-to)	1775-1778
Number of pages	4
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	3
Publication status	Published - 1989
Event	1989 International Conference on Acoustics, Speech, and Signal Processing - Glasgow, Scotland Duration: 1989 May 23 → 1989 May 26

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Cite this

@article{ecbdf711b871424ea470fb6ca8b9961d,

title = "Neural network learning paradigms involving nonlinear spectral processing",

abstract = "Two neural network architectures involving nonlinear spectral transformations are described. The first architecture involves generalization of nonlinear matched-filtering techniques, yielding a network that is very fast in learning and recall as well as highly accurate in classification. The second architecture is hierarchical with a number of stages; after each stage, error detection is carried out, followed by nonlinear spectral transformations when the error measure is above threshold.",

author = "Ersoy, {O. K.} and D. Hong",

year = "1989",

language = "English",

volume = "3",

pages = "1775--1778",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "0736-7791",

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

note = "1989 International Conference on Acoustics, Speech, and Signal Processing ; Conference date: 23-05-1989 Through 26-05-1989",

}

TY - JOUR

T1 - Neural network learning paradigms involving nonlinear spectral processing

AU - Ersoy, O. K.

AU - Hong, D.

PY - 1989

Y1 - 1989

N2 - Two neural network architectures involving nonlinear spectral transformations are described. The first architecture involves generalization of nonlinear matched-filtering techniques, yielding a network that is very fast in learning and recall as well as highly accurate in classification. The second architecture is hierarchical with a number of stages; after each stage, error detection is carried out, followed by nonlinear spectral transformations when the error measure is above threshold.

AB - Two neural network architectures involving nonlinear spectral transformations are described. The first architecture involves generalization of nonlinear matched-filtering techniques, yielding a network that is very fast in learning and recall as well as highly accurate in classification. The second architecture is hierarchical with a number of stages; after each stage, error detection is carried out, followed by nonlinear spectral transformations when the error measure is above threshold.

UR - http://www.scopus.com/inward/record.url?scp=0024901084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024901084&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0024901084

SN - 0736-7791

VL - 3

SP - 1775

EP - 1778

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 1989 International Conference on Acoustics, Speech, and Signal Processing

Y2 - 23 May 1989 through 26 May 1989

ER -

Neural network learning paradigms involving nonlinear spectral processing

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this