Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1998-02-06
Phys. Rev. E 59, 3386 (1999)
Physics
Condensed Matter
Disordered Systems and Neural Networks
26 pages, 10 ps figures
Scientific paper
10.1103/PhysRevE.59.3386
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.
Erichsen R. Jr.
Bolle D.
No associations
LandOfFree
A canonical ensemble approach to graded-response perceptrons does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A canonical ensemble approach to graded-response perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A canonical ensemble approach to graded-response perceptrons will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-423753