GERL, F and KREY, U (1994) STORAGE CAPACITY AND OPTIMAL LEARNING OF POTTS-MODEL PERCEPTRONS BY A CAVITY METHOD. JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 27 (22). pp. 7353-7372. ISSN 0305-4470,
Full text not available from this repository.Abstract
By means of a general formulation for the optimal learning capacity of perceptrons with multi-state neurons and real-valued couplings with spherical constraints, which we derive by a cavity method, we calculate the optimal learning capacity alpha(c)(Q', kappa) := p(max)/[N(Q - 1)] for perceptrons with a Q- resp. Q'-state Potts-model input resp. output neurons as a function of Q' and the stability parameter kappa. Among other results, the asymptote for Q' --> infinity is found, and it is shown that for kappa = 0 the information gain per coupling, DELTA I = (alpha(c) ln Q')/(Q' - 1), converges slowly to 1/2 in this limit. Moreover, for Q' --> infinity the same asymptotics also apply for the simple case of Hebbian learning.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | NEURAL NETWORKS; ALGORITHM; ADATRON; |
| Depositing User: | Dr. Gernot Deinzer |
| Last Modified: | 19 Oct 2022 08:39 |
| URI: | https://pred.uni-regensburg.de/id/eprint/52969 |
Actions (login required)
 |
View Item |
