Skip to main content
Kent Academic Repository

The magnitude of the diagonal elements in neural networks

De Wilde, Philippe (1997) The magnitude of the diagonal elements in neural networks. Neural Networks, 10 (3). pp. 499-504. ISSN 0893-6080. (doi:10.1016/S0893-6080(96)00094-9) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:93393)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL:
https://doi.org/10.1016/S0893-6080(96)00094-9

Abstract

The weights of completely connected neural networks are usually derived from the sum-of-outer products rule, with zero diagonal in the weight matrix. In this paper, we calculate what the magnitude of the diagonal elements should be in order to obtain a capacity that is linear in the number of neurons, with the proportionality factor chosen by the user of the network. The theoretical results are verified with simulations. We also show how to obtain the optimal magnitude for the diagonal elements and we investigate the number of spurious patterns. We assume several statistical independence conditions. The theoretical calculations are valid in the limit for an infinite number of neurons. The simulations provide results for networks of a finite size.

Item Type: Article
DOI/Identification number: 10.1016/S0893-6080(96)00094-9
Uncontrolled keywords: associative memory, capacity, diagonal, hysteresis, neural networks, self-coupling, self-feedback, spurio us patterns
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Philippe De Wilde
Date Deposited: 03 Jan 2023 16:43 UTC
Last Modified: 04 Jan 2023 11:46 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/93393 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.