The Kanerva memory is stable
Resource
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Journal
IJCNN-91-Seattle International Joint Conference on Neural Networks, 1991
Pages
-
Date Issued
1991-07
Date
1991-07
Author(s)
Goodman, Rodney M.
DOI
N/A
Abstract
The Kanerva memory is a simple yet important model of the cerebellar cortex. Its power has been demonstrated by its huge storage capacity as an associative memory. In the present work, the Kanerva memory is briefly introduced and it is shown to be asymptotically stable in both the parallel update and sequential update modes. Its asymptotic stability is proved by introducing a Lyapunov function and showing that the function follows a descent trajectory as the Kanerva memory evolves.>
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00155349.pdf
Size
192.85 KB
Format
Adobe PDF
Checksum
(MD5):3fb39ae83cec098a95b8b3961536a8a2