Abstract
A new optical architecture is described for the realization of distance-based classifiers and, in particular, radial basis function classifiers. This new system uses spatial multiplexing to improve computation speed while simple parallel postprocessing electronics are used to provide on-line learning in the optical neural network. This architecture is compared with a previous optical system which realized a radial basis function classifier in the solution of the handwritten digit recognition problem.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
| Publisher | Publ by Int Soc for Optical Engineering |
| Pages | 250-255 |
| Number of pages | 6 |
| Volume | 1469 |
| Edition | pt 1 |
| ISBN (Print) | 0819405787 |
| State | Published - 1991 |
| Externally published | Yes |
| Event | Applications of Artificial Neural Networks II - Orlando, FL, USA Duration: Apr 2 1991 → Apr 5 1991 |
Other
| Other | Applications of Artificial Neural Networks II |
|---|---|
| City | Orlando, FL, USA |
| Period | 4/2/91 → 4/5/91 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics
Cite this
Handwritten zip code recognition using an optical radial basis function classifier. / Neifeld, Mark A; Rakshit, S.; Psaltis, Demetri.
Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1469 pt 1. ed. Publ by Int Soc for Optical Engineering, 1991. p. 250-255.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Handwritten zip code recognition using an optical radial basis function classifier
AU - Neifeld, Mark A
AU - Rakshit, S.
AU - Psaltis, Demetri
PY - 1991
Y1 - 1991
N2 - A new optical architecture is described for the realization of distance-based classifiers and, in particular, radial basis function classifiers. This new system uses spatial multiplexing to improve computation speed while simple parallel postprocessing electronics are used to provide on-line learning in the optical neural network. This architecture is compared with a previous optical system which realized a radial basis function classifier in the solution of the handwritten digit recognition problem.
AB - A new optical architecture is described for the realization of distance-based classifiers and, in particular, radial basis function classifiers. This new system uses spatial multiplexing to improve computation speed while simple parallel postprocessing electronics are used to provide on-line learning in the optical neural network. This architecture is compared with a previous optical system which realized a radial basis function classifier in the solution of the handwritten digit recognition problem.
UR - http://www.scopus.com/inward/record.url?scp=0025846176&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0025846176&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0025846176
SN - 0819405787
VL - 1469
SP - 250
EP - 255
BT - Proceedings of SPIE - The International Society for Optical Engineering
PB - Publ by Int Soc for Optical Engineering
ER -