Storage capacity of a neural network with state-dependent synapses
Por:
Zertuche F., Lopez R., Waelbroeck H.
Publicada:
1 ene 1994
Resumen:
The storage capacity of the Hopfield network is limited to p/N <or= alpha c=0.138 (p=number of patterns, N=number of neurons), beyond which the contribution of weakly correlated patterns surpasses that of the desired pattern. This contribution can be eliminated by introducing a threshold: a pattern correlation below this threshold is simply set to zero in the synapses. We solve the mean-field equations and derive the critical value of the threshold required to stabilize p= alpha N patterns with alpha > alpha c.
Filiaciones:
Zertuche F.:
Inst. de Investigaciones en Matematicas Apl. y en Sist., UNAM, Cuernavaca, Mexico
|