Share Email Print
cover

Proceedings Paper

Invariance in an optoelectronic implementation of neural networks
Author(s): Yizhak Idan; Raymond C. Chevallier; Kevin J. Heggarty; Gabriel Y. Sirat
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Two dimensional jmuem recognition related tasks require the introduction of invariant recognition ftors such as shift, rotation, scale and deformation. In a preliminary work' we showed the inherent capability of our FMR coding to perform shift-invariant retrieval. This capability is essential for other invariances which can be transformed into translated representations. In this paper we propose using this translation invariant coding in a general scheme, whereby a we-processor handles the invariance issues and aligns the input probe to a fixed baseline utilized by the recognition mechanism. This higher order layer includes S "validation switches", each switch corresponding to a position index of translated objects. A validation switch will be eon" f the stimulus matches one of the objects, translated to the position handled by this switch. These switches condition the search, and where a search is needed, they supply the required transformation for stimulus alignment. Several proximity measures, needed for the realization of these switches, are presented and compared, in the context of different weight prescription algorithms.

Paper Details

Date Published: 1 August 1990
PDF: 6 pages
Proc. SPIE 1281, Optical Interconnections and Networks, (1 August 1990); doi: 10.1117/12.20688
Show Author Affiliations
Yizhak Idan, Telecom Paris (France)
Raymond C. Chevallier, Telecom Paris (France)
Kevin J. Heggarty, Telecom Paris (France)
Gabriel Y. Sirat, Telecom Paris (France)


Published in SPIE Proceedings Vol. 1281:
Optical Interconnections and Networks
Hartmut Bartelt, Editor(s)

© SPIE. Terms of Use
Back to Top