Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · Journal of Physics A Mathematical and General · 1991

Replica symmetry breaking in neural networks with modified pseudo-inverse interactions

Виктор Степанович Доценко, Brunello Tirozzi

Cited by 16Abstract and details only

Abstract

Replica symmetry breaking is studied in fully connected neural networks with modified pseudo-inverse interactions. The interaction matrix has an intermediate form between the Hebb learning rule and the pseudo-inverse one. At low temperatures there is a region of parameters where the replica symmetric solution is stable while its entropy is negative. It indicates the existence of an alternative solution in which the replica symmetry is broken. The one-step replica symmetry-breaking solution is found and its properties are analysed.

Cite this paper

APA 7

Доценко, В. С., & Tirozzi, B. (1991). Replica symmetry breaking in neural networks with modified pseudo-inverse interactions. Journal of Physics A Mathematical and General, 24(21), 5163–5180. https://doi.org/10.1088/0305-4470/24/21/026

MLA 9

Доценко, Виктор Степанович, and Brunello Tirozzi. “Replica symmetry breaking in neural networks with modified pseudo-inverse interactions.” Journal of Physics A Mathematical and General, vol. 24, no. 21, 1991, pp. 5163–80, https://doi.org/10.1088/0305-4470/24/21/026.

Chicago

Доценко, Виктор Степанович, and Brunello Tirozzi. 1991. “Replica symmetry breaking in neural networks with modified pseudo-inverse interactions.” Journal of Physics A Mathematical and General 24 (21): 5163–80. https://doi.org/10.1088/0305-4470/24/21/026.

Harvard

Доценко, В.С. and Tirozzi, B. (1991) ‘Replica symmetry breaking in neural networks with modified pseudo-inverse interactions’, Journal of Physics A Mathematical and General, 24(21), pp. 5163–5180. Available at: https://doi.org/10.1088/0305-4470/24/21/026.

BibTeX
@article{anon1991replica,
  title = {{Replica symmetry breaking in neural networks with modified pseudo-inverse interactions}},
  author = {Доценко, Виктор Степанович and Tirozzi, Brunello},
  journal = {Journal of Physics A Mathematical and General},
  volume = {24},
  number = {21},
  pages = {5163--5180},
  year = {1991},
  doi = {10.1088/0305-4470/24/21/026}
}

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

Related papers