Skip to main content

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

Publication ,  Journal Article
Brunel, N
Published in: Journal of Physics A: Mathematical and General
December 1, 1994

The storage capacity in an attractor neural network with excitatory couplings 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 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 are supported by numerical simulations done with an exhaustive search algorithm, and partly solve in the sparse coding limit the paradox of the discrepancy of the capacity of the Willshaw model with optimal capacity.

Duke Scholars

Published In

Journal of Physics A: Mathematical and General

DOI

ISSN

0305-4470

Publication Date

December 1, 1994

Volume

27

Issue

14

Start / End Page

4783 / 4789

Related Subject Headings

  • Mathematical Physics
  • 51 Physical sciences
  • 49 Mathematical sciences
  • 02 Physical Sciences
  • 01 Mathematical Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Brunel, N. (1994). 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), 4783–4789. https://doi.org/10.1088/0305-4470/27/14/009
Brunel, Nicolas. “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, no. 14 (December 1, 1994): 4783–89. https://doi.org/10.1088/0305-4470/27/14/009.
Brunel N. Storage capacity of neural networks: Effect of the fluctuations of the number of active neurons per memory. Journal of Physics A: Mathematical and General. 1994 Dec 1;27(14):4783–9.
Brunel, Nicolas. “Storage capacity of neural networks: Effect of the fluctuations of the number of active neurons per memory.” Journal of Physics A: Mathematical and General, vol. 27, no. 14, Dec. 1994, pp. 4783–89. Manual, doi:10.1088/0305-4470/27/14/009.
Brunel N. Storage capacity of neural networks: Effect of the fluctuations of the number of active neurons per memory. Journal of Physics A: Mathematical and General. 1994 Dec 1;27(14):4783–4789.

Published In

Journal of Physics A: Mathematical and General

DOI

ISSN

0305-4470

Publication Date

December 1, 1994

Volume

27

Issue

14

Start / End Page

4783 / 4789

Related Subject Headings

  • Mathematical Physics
  • 51 Physical sciences
  • 49 Mathematical sciences
  • 02 Physical Sciences
  • 01 Mathematical Sciences