Ho, A.M.C.L., De Wilde, Philippe (1995) General transient length upper bound for recurrent neural networks. In: Lecture Notes in Computer Science. From Natural to Artificial Neural Computation. IWANN 1995. 930. pp. 202-208. Springer ISBN 978-3-540-59497-0. (doi:10.1007/3-540-59497-3_176) (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:93396)
| 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/10.1111/10.1007/3-540-59497-3_176 |
Abstract
We show how to construct a Lyapunov function for a discrete recurrent neural network using the variable-gradient method, This method can also be used to obtain the Hopfield energy function. Using our Lyapunov function, we compute an upper bound for the transient length for our neural network dynamics. We also show how our Lyapunov function can provide insights into the effect that the introduction of self-feedback weights to our neural network has on the sizes of the basins of attraction of the equilibrium points of the neural network state space.
| Item Type: | Conference or workshop item (Paper) |
|---|---|
| DOI/Identification number: | 10.1007/3-540-59497-3_176 |
| Uncontrolled keywords: | neural networks |
| 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 16:36 UTC |
| Last Modified: | 05 Nov 2024 12:58 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/93396 (The current URI for this page, for reference purposes) |
University of Kent Author Information
De Wilde, Philippe.
| Creator's ORCID: |
 https://orcid.org/0000-0002-4332-1715
|
|---|---|
| CReDIT Contributor Roles: |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):
Altmetric
Altmetric
