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 language | English |
|---|---|
| Pages (from-to) | 1910-1913 |
| Number of pages | 4 |
| Journal | Japanese Journal of Applied Physics |
| Volume | 33 |
| Issue number | 4R |
| DOIs | |
| Publication status | Published - 1994 Apr |
ASJC Scopus subject areas
- Engineering(all)
- Physics and Astronomy(all)
Fingerprint Dive into the research topics of 'Trainable pattern classifier using a computer-generated hologram'. Together they form a unique fingerprint.
Cite this
Yuh, K., & Cheng, C. J. (1994). Trainable pattern classifier using a computer-generated hologram. Japanese Journal of Applied Physics, 33(4R), 1910-1913. https://doi.org/10.1143/JJAP.33.1910