Skip to content
Free planNo credit card requiredStart writing

article · Journal of Physics A Mathematical and General · 1992

Modified pseudo-inverse neural networks storing correlated patterns

Ralf Der, Виктор Степанович Доценко, Brunello Tirozzi

Cited by 4Abstract and details only

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/ln(1/p) -1 ) where p<<1 is the average neural activity) can be achieved by appropriate adjustment of the threshold term of the Hamiltonian.

Cite this paper

APA 7

Der, R., Доценко, В. С., & Tirozzi, B. (1992). Modified pseudo-inverse neural networks storing correlated patterns. Journal of Physics A Mathematical and General, 25(10), 2843–2857. https://doi.org/10.1088/0305-4470/25/10/013

MLA 9

Der, Ralf, et al. “Modified pseudo-inverse neural networks storing correlated patterns.” Journal of Physics A Mathematical and General, vol. 25, no. 10, 1992, pp. 2843–57, https://doi.org/10.1088/0305-4470/25/10/013.

Chicago

Der, Ralf, Виктор Степанович Доценко, and Brunello Tirozzi. 1992. “Modified pseudo-inverse neural networks storing correlated patterns.” Journal of Physics A Mathematical and General 25 (10): 2843–57. https://doi.org/10.1088/0305-4470/25/10/013.

Harvard

Der, R., Доценко, В.С. and Tirozzi, B. (1992) ‘Modified pseudo-inverse neural networks storing correlated patterns’, Journal of Physics A Mathematical and General, 25(10), pp. 2843–2857. Available at: https://doi.org/10.1088/0305-4470/25/10/013.

BibTeX
@article{der1992modified,
  title = {{Modified pseudo-inverse neural networks storing correlated patterns}},
  author = {Der, Ralf and Доценко, Виктор Степанович and Tirozzi, Brunello},
  journal = {Journal of Physics A Mathematical and General},
  volume = {25},
  number = {10},
  pages = {2843--2857},
  year = {1992},
  doi = {10.1088/0305-4470/25/10/013}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.