Share Email Print

Proceedings Paper

Natural learning of neural networks by reconfiguration
Author(s): Lambert Spaanenburg; R. Alberts; Cornelis H. Slump; B. J. vanderZwaag
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

The communicational and computational demands of neural networks are hard to satisfy in a digital technology. Temporal computing addresses this problem by iteration, but leaves a slow network. Spatial computing only became an option with the coming of modern FPGA devices. The paper provides two examples. First the balance between area and time is discussed on the realization of a modular feed-forward network. Second, the design of real-time image processing through a Cellular Neural Network is treated. In both examples, reconfiguration can be applied to provide for a natural and transparent support of learning.

Paper Details

Date Published: 18 April 2003
PDF: 12 pages
Proc. SPIE 5119, Bioengineered and Bioinspired Systems, (18 April 2003); doi: 10.1117/12.499549
Show Author Affiliations
Lambert Spaanenburg, Lund Univ. (Sweden)
R. Alberts, Lund Univ. (Sweden)
Cornelis H. Slump, Univ. Twente (Netherlands)
B. J. vanderZwaag, Univ. Twente (Netherlands)

Published in SPIE Proceedings Vol. 5119:
Bioengineered and Bioinspired Systems
Angel Rodriguez-Vazquez; Derek Abbott; Ricardo Carmona, Editor(s)

© SPIE. Terms of Use
Back to Top