caa a22 4500 477034209 CHVBK 20180405111301.0 cr unu---uuuuu 170330e19960901xx s 000 0 eng 10.1007/BF00454841 doi (NATIONALLICENCE)springer-10.1007/BF00454841 A novel approach for analyzing dynamics in neural networks with saturated characteristics [Elektronische Daten] [Jianfeng Feng, David Brown] Current theories about the dynamics of neural networks with nonlinear characteristics and parameterized by set of parameters are mostly based on approximations in one way or another. In this paper we first introduce a rigorous approach which allows us to check in which parameter region a given saturated state is an attractor of the dynamics: a saturated state w=(w i , i=1,...,N)∈{-1,1} N is an attractor of the dynamics if and only if there is a local field gap between neurons in J + (w)={i, w i =1} and J - (w)={i, w i =−1}. Then we apply the result to analyze several models in neural networks. In particular in the Hopfield model we calculate the capacity and give an exact relation between the capacity and the threshold. Kluwer Academic Publishers, 1996 capacity nationallicence Hopfield model nationallicence Linsker's model nationallicence saturated characteristic nationallicence Feng Jianfeng Laboratory of Biomathematics, The Babraham Institute, CB2 4AT, Cambridge, UK aut Brown David Laboratory of Biomathematics, The Babraham Institute, CB2 4AT, Cambridge, UK aut Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 4/1(1996-09-01), 9-16 1370-4621 4:1<9 1996 4 11063 https://doi.org/10.1007/BF00454841 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00454841 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Feng Jianfeng Laboratory of Biomathematics, The Babraham Institute, CB2 4AT, Cambridge, UK aut NATIONALLICENCE 700 1- Brown David Laboratory of Biomathematics, The Babraham Institute, CB2 4AT, Cambridge, UK aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 4/1(1996-09-01), 9-16 1370-4621 4:1<9 1996 4 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer