Hierarchical neural network involving nonlinear spectral processing

O. K. Ersoy, D. Hong

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Summary form only given, as follows. A new neural network architecture called the hierarchical neural network (HNN) is introduced. The HNN involves a number of stages in which each stage can be a particular neural network (SNN). Between two SNNs there is a nonlinear transformation of those input vectors rejected by the first SNN. The HNN has many desirable properties such as optimized system complexity in the sense of minimized number of stages, high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all SNNs are operating simultaneously without waiting for data from each other. The experiments performed in comparison to multilayered networks with backpropagation training indicated the superiority of the HNN.

Original languageEnglish
Number of pages1
Publication statusPublished - 1989 Dec 1
EventIJCNN International Joint Conference on Neural Networks - Washington, DC, USA
Duration: 1989 Jun 181989 Jun 22

Other

OtherIJCNN International Joint Conference on Neural Networks
CityWashington, DC, USA
Period89/6/1889/6/22

Fingerprint

Neural networks
Processing
Parallel architectures
Network architecture
Backpropagation
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Ersoy, O. K., & Hong, D. (1989). Hierarchical neural network involving nonlinear spectral processing. Paper presented at IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, .
Ersoy, O. K. ; Hong, D. / Hierarchical neural network involving nonlinear spectral processing. Paper presented at IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, .1 p.
@conference{582abfe06f054383a55e6ccb416d44d7,
title = "Hierarchical neural network involving nonlinear spectral processing",
abstract = "Summary form only given, as follows. A new neural network architecture called the hierarchical neural network (HNN) is introduced. The HNN involves a number of stages in which each stage can be a particular neural network (SNN). Between two SNNs there is a nonlinear transformation of those input vectors rejected by the first SNN. The HNN has many desirable properties such as optimized system complexity in the sense of minimized number of stages, high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all SNNs are operating simultaneously without waiting for data from each other. The experiments performed in comparison to multilayered networks with backpropagation training indicated the superiority of the HNN.",
author = "Ersoy, {O. K.} and D. Hong",
year = "1989",
month = "12",
day = "1",
language = "English",
note = "IJCNN International Joint Conference on Neural Networks ; Conference date: 18-06-1989 Through 22-06-1989",

}

Ersoy, OK & Hong, D 1989, 'Hierarchical neural network involving nonlinear spectral processing', Paper presented at IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, 89/6/18 - 89/6/22.

Hierarchical neural network involving nonlinear spectral processing. / Ersoy, O. K.; Hong, D.

1989. Paper presented at IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Hierarchical neural network involving nonlinear spectral processing

AU - Ersoy, O. K.

AU - Hong, D.

PY - 1989/12/1

Y1 - 1989/12/1

N2 - Summary form only given, as follows. A new neural network architecture called the hierarchical neural network (HNN) is introduced. The HNN involves a number of stages in which each stage can be a particular neural network (SNN). Between two SNNs there is a nonlinear transformation of those input vectors rejected by the first SNN. The HNN has many desirable properties such as optimized system complexity in the sense of minimized number of stages, high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all SNNs are operating simultaneously without waiting for data from each other. The experiments performed in comparison to multilayered networks with backpropagation training indicated the superiority of the HNN.

AB - Summary form only given, as follows. A new neural network architecture called the hierarchical neural network (HNN) is introduced. The HNN involves a number of stages in which each stage can be a particular neural network (SNN). Between two SNNs there is a nonlinear transformation of those input vectors rejected by the first SNN. The HNN has many desirable properties such as optimized system complexity in the sense of minimized number of stages, high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all SNNs are operating simultaneously without waiting for data from each other. The experiments performed in comparison to multilayered networks with backpropagation training indicated the superiority of the HNN.

UR - http://www.scopus.com/inward/record.url?scp=0024881278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024881278&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0024881278

ER -

Ersoy OK, Hong D. Hierarchical neural network involving nonlinear spectral processing. 1989. Paper presented at IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, .