Trainable pattern classifier using a computer-generated hologram

Research output: Contribution to journalArticle

Abstract

A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.

Original languageEnglish
Pages (from-to)1910-1913
Number of pages4
JournalJapanese Journal of Applied Physics
Volume33
Issue number4R
DOIs
Publication statusPublished - 1994 Apr

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)
  • Physics and Astronomy(all)

Cite this