Storage capacity of neural networks : effect of the fluctuations of the number of active neurons per memory

@inproceedings{Brunelt2002StorageCO,
  title={Storage capacity of neural networks : effect of the fluctuations of the number of active neurons per memory},
  author={Nicolas Brunelt and de Physique Statistiquet and Nomale Superieure},
  year={2002}
}
  • Nicolas Brunelt, de Physique Statistiquet, Nomale Superieure
  • Published 2002
The storage capacity in an amactor neural network with excitatory couplings is shown to depend not only on the h a i o n 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 the case of exactly the same number of active neurons in every pattern. For every coding level the capacity is increased with respect to the case of random patterns. Results m t supponed by numerical simulations done with… CONTINUE READING