A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.

Benoit Siri (1) , Hugues Berry (2, 1) , Bruno Cessac (3, 4, 5) , Bruno Delord (6) , Mathias Quoy (7)

1 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
2 Inria Grenoble - Rhône-Alpes
3 JAD - Laboratoire Jean Alexandre Dieudonné
4 ODYSSEE - Computer and biological vision
5 INLN - Institut Non Linéaire de Nice Sophia-Antipolis
6 ISIR - Institut des Systèmes Intelligents et Robotique
7 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes

Domaines: Architectures Matérielles [cs.AR]; Neurosciences

Benoit Siri, Hugues Berry, Bruno Cessac, Bruno Delord, Mathias Quoy. A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.. Neural Computation, 2008, 20, pp.2937-2966. ⟨inria-00633582⟩