arXiv · cond-mat/9802075
A canonical ensemble approach to graded-response perceptrons
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
D. Bolle, R. Erichsen Jr. 1998-02-06. A canonical ensemble approach to graded-response perceptrons. https://doi.org/10.1103/physreve.59.3386
Cite the original work for its findings. Save a collection to share your selection of sources.