English

A canonical ensemble approach to graded-response perceptrons

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

Abstract

Perceptrons with graded input-output relations and a limited output precision are studied within the Gardner-Derrida canonical ensemble approach. Soft non- negative error measures are introduced allowing for extended retrieval properties. In particular, the performance of these systems for a linear and quadratic error measure, corresponding to the perceptron respectively the adaline learning algorithm, is compared with the performance for a rigid error measure, simply counting the number of errors. Replica-symmetry-breaking effects are evaluated.

Keywords

Cite

@article{arxiv.cond-mat/9802075,
  title  = {A canonical ensemble approach to graded-response perceptrons},
  author = {D. Bolle and R. Erichsen},
  journal= {arXiv preprint arXiv:cond-mat/9802075},
  year   = {2009}
}

Comments

26 pages, 10 ps figures