Share Email Print

Proceedings Paper

Controlled redundancy in interpolation-based neural nets
Author(s): Harsha M. Wabgaonkar; Allen R. Stubberud
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we deal with the problem of associative memory synthesis via multivariate interpolation. We present an abstract yet simple formalism to address the possibility of detecting and eliminating redundant input data from the set of exemplars. The remaining pairs are then stored in a way so as to introduce controlled redundancy by replication of the corresponding neurons. The redundancy is detected via orthogonalization carried out in a Reproducing Kernel Hilbert Space setting.

Paper Details

Date Published: 1 February 1992
PDF: 10 pages
Proc. SPIE 1610, Curves and Surfaces in Computer Vision and Graphics II, (1 February 1992); doi: 10.1117/12.135131
Show Author Affiliations
Harsha M. Wabgaonkar, Univ. of California/Irvine (United States)
Allen R. Stubberud, Univ. of California/Irvine (United States)

Published in SPIE Proceedings Vol. 1610:
Curves and Surfaces in Computer Vision and Graphics II
Martine J. Silbermann; Hemant D. Tagare, Editor(s)

© SPIE. Terms of Use
Back to Top