A neural network model as a globally coupled map and applications based on chaos
Abstract
First, a neural network model as the globally coupled map (GCM) is proposed. The model is obtained by modification of a Hopfield network model that has a negative self-feedback connection. Second, information processed by this model is interpreted in terms of the variety of the maps acting on the network elements, and a new, dynamic information processing model is described. The search for information using vague keywords, and solution of the traveling salesman problem (TSP) are introduced as applications.
- Publication:
-
Chaos
- Pub Date:
- July 1992
- DOI:
- 10.1063/1.165880
- Bibcode:
- 1992Chaos...2..377N