N. Brunel, STORAGE CAPACITY OF NEURAL NETWORKS - EFFECT OF THE FLUCTUATIONS OF THE NUMBER OF ACTIVE NEURONS PER MEMORY, Journal of physics. A, mathematical and general, 27(14), 1994, pp. 4783-4789
The storage capacity in an attractor neural network with excitatory co
uplings is shown to depend not only on the fraction of active neurons
per pattern (or coding rate), but also on the fluctuations around this
value, in the thermodynamical limit. The capacity is calculated in th
e case of exactly the same number of active neurons in every pattern.
For every coding level the capacity is increased with respect to the c
ase of random patterns. Results are supported by numerical simulations
done with an exhaustive search algorithm, and partly solve in the spa
rse coding limit the paradox of the discrepancy of the capacity of the
Willshaw model with optimal capacity.