English

Thresholds in layered neural networks with variable activity

Disordered Systems and Neural Networks 2009-10-31 v1 Statistical Mechanics q-bio

Abstract

The inclusion of a threshold in the dynamics of layered neural networks with variable activity is studied at arbitrary temperature. In particular, the effects on the retrieval quality of a self-controlled threshold obtained by forcing the neural activity to stay equal to the activity of the stored paterns during the whole retrieval process, are compared with those of a threshold chosen externally for every loading and every temperature through optimisation of the mutual information content of the network. Numerical results, mostly concerning low activity networks are discussed.

Keywords

Cite

@article{arxiv.cond-mat/9909443,
  title  = {Thresholds in layered neural networks with variable activity},
  author = {D. Bolle' and G. Massolo},
  journal= {arXiv preprint arXiv:cond-mat/9909443},
  year   = {2009}
}

Comments

15 pages, Latex2e, 6 eps figures