Reinforced walk on graphs and neural networks
Studia Mathematica 189 (2008), 255-268 MSC: Primary 60K37; Secondary 60J10, 60J20, 60G50, 82C41. DOI: 10.4064/sm189-3-4
A directed-edge-reinforced random walk on graphs is considered. Criteria for the walk to end up in a limit cycle are given. Asymptotic stability of some neural networks is shown.