Design of one-pass training algorithms for variant morphological operations

Jenlong Moh, Frank Y. Shih

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

In this paper, the design of one-pass training algorithms for variant morphological operations is presented. The algorithms intend to achieve a fast-learning goal in which the morphological neurons can learn a training pattern and memorize it in exactly one training iteration. Furthermore, only simple computations are used to allow easy implementation in hardware. The proofs of the training algorithms and the program-simulated experimental results are provided.

Original languageEnglish (US)
Pages (from-to)303-314
Number of pages12
JournalInformation sciences
Volume94
Issue number1-4
DOIs
StatePublished - Oct 1996

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Design of one-pass training algorithms for variant morphological operations'. Together they form a unique fingerprint.

Cite this