A neural architecture for hierarchical clustering

A. Bouzerdoum; M. L. Southcott; J. Zhu; R. E. Bogner

doi:10.1109/ICASSP.1994.389569

A neural architecture for hierarchical clustering

A. Bouzerdoum, M. L. Southcott, J. Zhu, R. E. Bogner

HBKU College of Science and Engineering

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

Abstract

An hierarchical neural network structure for clustering problems is presented and a statistical analysis of its performance is conducted. This neural network architecture aims to find, through competition and cooperation, maximally related objects in a scene. The architecture was first introduced by Maren and Ali (1983), and was named the hierarchical scene structure (HSS). We propose an enhancement of the original HSS and demonstrate that this leads to an improved performance. It is also shown that further improvement in performance can be achieved by cascading two enhanced HSS networks.

Original language	English
Article number	389569
Pages (from-to)	II661-II664
Journal	Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Volume	2
DOIs	https://doi.org/10.1109/ICASSP.1994.389569
Publication status	Published - 1994
Event	Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust Duration: 19 Apr 1994 → 22 Apr 1994

Access to Document

10.1109/ICASSP.1994.389569

Cite this

@article{4a5e471287714da0b0491976b399db5e,

title = "A neural architecture for hierarchical clustering",

abstract = "An hierarchical neural network structure for clustering problems is presented and a statistical analysis of its performance is conducted. This neural network architecture aims to find, through competition and cooperation, maximally related objects in a scene. The architecture was first introduced by Maren and Ali (1983), and was named the hierarchical scene structure (HSS). We propose an enhancement of the original HSS and demonstrate that this leads to an improved performance. It is also shown that further improvement in performance can be achieved by cascading two enhanced HSS networks.",

author = "A. Bouzerdoum and Southcott, {M. L.} and J. Zhu and Bogner, {R. E.}",

note = "Publisher Copyright: {\textcopyright} 1994 IEEE.; Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) ; Conference date: 19-04-1994 Through 22-04-1994",

year = "1994",

doi = "10.1109/ICASSP.1994.389569",

language = "English",

volume = "2",

pages = "II661--II664",

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

issn = "0736-7791",

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

}

TY - JOUR

T1 - A neural architecture for hierarchical clustering

AU - Bouzerdoum, A.

AU - Southcott, M. L.

AU - Zhu, J.

AU - Bogner, R. E.

PY - 1994

Y1 - 1994

N2 - An hierarchical neural network structure for clustering problems is presented and a statistical analysis of its performance is conducted. This neural network architecture aims to find, through competition and cooperation, maximally related objects in a scene. The architecture was first introduced by Maren and Ali (1983), and was named the hierarchical scene structure (HSS). We propose an enhancement of the original HSS and demonstrate that this leads to an improved performance. It is also shown that further improvement in performance can be achieved by cascading two enhanced HSS networks.

AB - An hierarchical neural network structure for clustering problems is presented and a statistical analysis of its performance is conducted. This neural network architecture aims to find, through competition and cooperation, maximally related objects in a scene. The architecture was first introduced by Maren and Ali (1983), and was named the hierarchical scene structure (HSS). We propose an enhancement of the original HSS and demonstrate that this leads to an improved performance. It is also shown that further improvement in performance can be achieved by cascading two enhanced HSS networks.

UR - http://www.scopus.com/inward/record.url?scp=85079276746&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1994.389569

DO - 10.1109/ICASSP.1994.389569

M3 - Conference article

AN - SCOPUS:85079276746

SN - 0736-7791

VL - 2

SP - II661-II664

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

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

M1 - 389569

T2 - Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6)

Y2 - 19 April 1994 through 22 April 1994

ER -

A neural architecture for hierarchical clustering

Abstract

Access to Document

Other files and links

Fingerprint

Cite this