Parallel, self-organizing, hierarchical neural networks for vision and systems control

O. K. Ersoy, D. Hong

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

Abstract

A new neural network architecture called the parallel self-organizing hierarchical neural network (PSHNN) is presented. This new architecture involves a number of stages in which each stage can be a particular neural network (SNN). At the end of each stage, error detection is carried out, and a number of input vectors are rejected. Between two stages there is a nonlinear transformation of those input vectors rejected by the previous stage. The new architecture has many desirable properties such as optimized system complexity in the sense of minimized self-organizing number of stages, high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all stages are operating simultaneously without waiting for data from each other during testing. The experiments performed in comparison to multilayered networks with backpropagation training indicated the superiority of the new architecture.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Intelligent Motion Control, IMC 1990
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages193-198
Number of pages6
ISBN (Electronic)9780000000002
DOIs
Publication statusPublished - 1990 Jan 1
Event1990 IEEE International Workshop on Intelligent Motion Control, IMC 1990 - Istanbul, Turkey
Duration: 1990 Aug 201990 Aug 22

Publication series

NameProceedings of the IEEE International Workshop on Intelligent Motion Control, IMC 1990
Volume1

Conference

Conference1990 IEEE International Workshop on Intelligent Motion Control, IMC 1990
CountryTurkey
CityIstanbul
Period90/8/2090/8/22

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Mechanical Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'Parallel, self-organizing, hierarchical neural networks for vision and systems control'. Together they form a unique fingerprint.

  • Cite this

    Ersoy, O. K., & Hong, D. (1990). Parallel, self-organizing, hierarchical neural networks for vision and systems control. In Proceedings of the IEEE International Workshop on Intelligent Motion Control, IMC 1990 (pp. 193-198). [687316] (Proceedings of the IEEE International Workshop on Intelligent Motion Control, IMC 1990; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMC.1990.687316