A recurrent neural network with ever changing synapses

Дата и время публикации : 2000-02-23T16:20:10Z

Авторы публикации и институты :
M. Heerema
W. A. van Leeuwen

Ссылка на журнал-издание: J. Phys. A: Math. Gen. 33 (2000)
Коментарии к cтатье: 17 pages, LaTeX, 4 figures
Первичная категория: cond-mat.dis-nn

Все категории : cond-mat.dis-nn, q-bio

Краткий обзор статьи: A recurrent neural network with noisy input is studied analytically, on the basis of a Discrete Time Master Equation. The latter is derived from a biologically realizable learning rule for the weights of the connections. In a numerical study it is found that the fixed points of the dynamics of the net are time dependent, implying that the representation in the brain of a fixed piece of information (e.g., a word to be recognized) is not fixed in time.

Category: Physics