Parallel, self-organizing hierarchical neural networks

O. K. Ersoy, D. Hong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A neural network architecture called the parallel self-organizing hierarchical neural network (PSHNN) is discussed. The PSHNN involves a number of stages in which each stage can be a particular neural network (SNN). At the end of each SNN, error detection is carried out, and a number of input vectors are rejected. Between two SNNs there is a nonlinear first SNN. The PSHNN has an optimized system complexity in the sense of minimized self-organizing number of stages, high classification accuracy, minimized learning and recall times, and parallel architectures in which all SNNs operate simultaneously without waiting for data from each other during testing. In classification experiments with aircraft and satellite remote-sensing data the PSHNN is compared to multilayer networks using backpropagation training.

Original languageEnglish
Title of host publicationProceedings of the Hawaii International Conference on System Science
EditorsLee W. Hoevel, Bruce D. Shriver, Jay F.Jr. Nunamaker, Ralph H.Jr. Sprague, Velijko Milutinovic
PublisherPubl by Western Periodicals Co
Pages158-169
Number of pages12
ISBN (Print)0818620080
Publication statusPublished - 1990
EventProceedings of the Twenty-Third Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track - Kailua-Kona, HI, USA
Duration: 1990 Jan 21990 Jan 5

Publication series

NameProceedings of the Hawaii International Conference on System Science
Volume1
ISSN (Print)0073-1129

Other

OtherProceedings of the Twenty-Third Annual Hawaii International Conference on System Sciences. Volume 1: Architecture Track
CityKailua-Kona, HI, USA
Period90/1/290/1/5

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Parallel, self-organizing hierarchical neural networks'. Together they form a unique fingerprint.

Cite this