scholarly journals Correlations between hidden units in multilayer neural networks and replica symmetry breaking

1999 ◽  
Vol 60 (2) ◽  
pp. 2097-2104
Author(s):  
D. Malzahn ◽  
A. Engel
1996 ◽  
Vol 07 (01) ◽  
pp. 19-32 ◽  
Author(s):  
A. LAMURA ◽  
C. MARANGI ◽  
G. NARDULLI

In this paper we analyze replica symmetry breaking in attractor neural networks with non-monotone activation function. We study the non-monotone version of the Edinburgh model, which allows the control of the domains of attraction by the stability parameter K, and we compute, at one step of symmetry breaking, storage capacity and, for the strongly dilute model, the domains of attraction of the stable fixed points.


2020 ◽  
Vol 53 (41) ◽  
pp. 415005 ◽  
Author(s):  
Elena Agliari ◽  
Linda Albanese ◽  
Adriano Barra ◽  
Gabriele Ottaviani

1995 ◽  
Vol 28 (24) ◽  
pp. 7105-7111 ◽  
Author(s):  
W Whyte ◽  
D Sherrington ◽  
K Y M Wong

1995 ◽  
Vol 28 (11) ◽  
pp. 3093-3107 ◽  
Author(s):  
V Dotsenko ◽  
A B Harris ◽  
D Sherrington ◽  
R B Stinchcombe

Sign in / Sign up

Export Citation Format

Share Document