Neural networks with symmetric couplings which have an intermediate form between the Hebb learning rule and the pseudo-inverse one, storing strongly correlated patterns, are studied. Signal-to-noise analysis is made and replica-symmetric thermodynamic Calculations are performed. Both approaches show that both in the Hopfield model limit and in the Pseudo-inverse model limit the maximal capacity of the order of (2p/In(1/p)-1 (where p << 1 is the average neural activity) can be achieved by appropriate adjustment of the threshold term of the Hamiltonian.
MODIFIED PSEUDO-INVERSE NEURAL NETWORKS STORING CORRELATED PATTERNS / R., Der; V. S., Dotsenko; Tirozzi, Benedetto. - In: JOURNAL OF PHYSICS. A, MATHEMATICAL AND GENERAL. - ISSN 0305-4470. - 25:10(1992), pp. 2843-2857. [10.1088/0305-4470/25/10/013]
MODIFIED PSEUDO-INVERSE NEURAL NETWORKS STORING CORRELATED PATTERNS
TIROZZI, Benedetto
1992
Abstract
Neural networks with symmetric couplings which have an intermediate form between the Hebb learning rule and the pseudo-inverse one, storing strongly correlated patterns, are studied. Signal-to-noise analysis is made and replica-symmetric thermodynamic Calculations are performed. Both approaches show that both in the Hopfield model limit and in the Pseudo-inverse model limit the maximal capacity of the order of (2p/In(1/p)-1 (where p << 1 is the average neural activity) can be achieved by appropriate adjustment of the threshold term of the Hamiltonian.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
