DocumentCode :
1319121
Title :
Generation of learning neighbourhood in Kohonen feature maps by means of simple nonlinear network
Author :
Heim, P. ; Hochet, B. ; Vittoz, E.
Author_Institution :
Electron. Lab., Swiss Federal Inst. of Technol., Lausanne, Switzerland
Volume :
27
Issue :
3
fYear :
1991
Firstpage :
275
Lastpage :
277
Abstract :
A simple CMOS analogue nonlinear network is presented which can be used as a very efficient means of defining the learning neighbourhood in analogue or digital VLSI realisations of Kohonen maps. The number of components is minimal and the detection of the neighbourhood is facilitated by a steep voltage drop at its boundary.
Keywords :
CMOS integrated circuits; VLSI; content-addressable storage; learning systems; network topology; neural nets; nonlinear network analysis; self-adjusting systems; 2D nonlinear network; CMOS analogue nonlinear network; Kohonen feature maps; analogue VLSI realisations; digital VLSI realisations; learning neighbourhood; orthogonal array topology; self-organising systems;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el:19910175
Filename :
83253
Link To Document :
بازگشت