Selviah, DR;
Midwinter, JE;
(1989)
Memory Capacity of a novel optical neural net architecture.
In:
(Proceedings) ONERA-CERT "Optics in Computing" International Symposium.
(pp. pp. 195-201).
ONERA-CERT: Toulouse, France.
![[thumbnail of 3417.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/application_pdf.png) Preview |
PDF
3417.pdf Download (179kB) |
Abstract
A new associative memory neural network which can be constructed using optical matched filters is described. It has three layers, the centre one being iterative with its weights set prior to training. The other two layers are feedforward nets and the weights are set during training. The best choice of central layer weights, or in optical terms, of pairs of images associated in a hologram is considered. The stored images or codes are selected carefully form an orthogonal set using a novel algorithm. This enables the net to have a high memory capacity equal to half the umber of neurons with a low probability of error. 17-18th October 1989.
| Type: | Proceedings paper |
|---|---|
| Title: | Memory Capacity of a novel optical neural net architecture |
| Event: | ONERA-CERT "Optics in Computing" International Symposium |
| Dates: | 17 October 1989 - 18 October 1989 |
| Open access status: | An open access version is available from UCL Discovery |
| Additional information: | Imported via OAI, 7:29:01 25th May 2007 |
| Keywords: | neural network, optical neural network, pattern recognition, threshold, discrimination, memory capacity |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/3417 |
Archive Staff Only
 |
View Item |
