Trainable pattern classifier using a computer-generated hologram

Ken-Yuh Hsu, Chau Jern Cheng

Research output: Contribution to journalArticlepeer-review


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
Issue number4R
StatePublished - 1 Jan 1994

Fingerprint Dive into the research topics of 'Trainable pattern classifier using a computer-generated hologram'. Together they form a unique fingerprint.

Cite this