Share Email Print

Proceedings Paper

Chaos, order, and associative memory in video feedback
Author(s): Gerd Haeusler; T. Neumahr; Lucas Parra; Harald Schoenfeld; B. Spellenberg
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A video image circulating in a loop with a local nonlinearity and a convolution operator can be considered as a high dimensional nonlinear dynamical system, or as a specific neural net. The evolving image displays spatiotemporal deterministic chaos, oscillations, and stable patterns. The specific behavior of the system is strongly determined by the coupling of pixels, i.e., by the synaptic pattern and by the nonlinearity. The system can be trained to display a certain given image as a fixed point. Thus, it is able to associatively restore perturbed input images, independently of a spatial shift.

Paper Details

Date Published: 1 December 1993
PDF: 8 pages
Proc. SPIE 2039, Chaos in Optics, (1 December 1993); doi: 10.1117/12.164774
Show Author Affiliations
Gerd Haeusler, Univ. Erlangen-Nuernberg (Germany)
T. Neumahr, Univ. Erlangen-Nuernberg (Germany)
Lucas Parra, Univ. Erlangen-Nuernberg (Germany)
Harald Schoenfeld, Univ. Erlangen-Nuernberg (Germany)
B. Spellenberg, Univ. Erlangen-Nuernberg (Germany)

Published in SPIE Proceedings Vol. 2039:
Chaos in Optics
Rajarshi Roy, Editor(s)

© SPIE. Terms of Use
Back to Top