hal-00179439, version 1
Stochastic analysis of the Abe formulation of Hopfield networks.
European Symposium on Artificial Neural Networks (2005) x
Abstract: This work studies the influence of random noise in the application of Hopfield networks to combinatorial optimization. It has been suggested that the Abe formulation, rather than the original Hopfield formulation, is better suited to optimization, but the eventual presence of noise in the connection weights of this model has not been considered up to now. This consideration leads to a model that is formulated as a stochastic differential equation. In the stochastic setting, the analysis reveals that the model is stable, and the states converge towards an attractive set, assuming the noise intensity is bounded. The relation of the attractor with that of the deterministic model requires further study.
- 1:
- CNRS : UMR8145 – Université Paris V - Paris Descartes
- 2:
- Université Paris I - Panthéon-Sorbonne
- 3:
- CNRS : UMR8595 – Université Paris I - Panthéon-Sorbonne
- 4:
- Universidad de Málaga
- 5:
- Universidad de Málaga
- Domain : Mathematics/Optimization and Control
Computer Science/Neural and Evolutionary Computing
Mathematics/Dynamical Systems
- hal-00179439, version 1
- http://hal.archives-ouvertes.fr/hal-00179439
- oai:hal.archives-ouvertes.fr:hal-00179439
- From:
- Submitted on: Monday, 15 October 2007 15:02:25
- Updated on: Tuesday, 16 October 2007 15:25:51



Export