The periodic behaviour of neural networks has been studied by several authors: In previous work we proved that symmetric neural networks admit only fixed points or two-cycles, here we analyze one and two-dimensional uniform neural arrays. Periodic structure of previous networks was first studied by R. Shingai using exhaustive analysis of the different local transition functions f. Our approach uses Lyapunov functions which permit us to obtain directly the periodic structure and also give bounds on the transient length.
|Número de páginas||1|
|Estado||Publicada - 1988|
|Publicado de forma externa||Sí|
|Evento||International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA|
Duración: 6 sep. 1988 → 10 sep. 1988