Properties and applications of weakly nonlinear neurons.

DOI10.1016/j.cam.2003.09.007zbMath1033.37043OpenAlexW2079736942WikidataQ123956608 ScholiaQ123956608MaRDI QIDQ1426758

Marek Kedzierski, Dariusz Jabłoński, Andrzej Bielecki

Publication date: 15 March 2004

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cam.2003.09.007

zbMATH Keywords

learning processartificial neural networksDynamical systemDiscretizationTopological conjugacy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural biology (92C20) Dynamical systems in biology (37N25) Neural networks for/in biological studies, artificial life and related topics (92B20) Topological and differentiable equivalence, conjugacy, moduli, classification of dynamical systems (37C15) Approximation methods and numerical treatment of dynamical systems (37M99)

Related Items

Dynamical properties of the reaction-diffusion type model of fast synaptic transport

Cites Work

• Shadowing property in analysis of neural networks dynamics.
• Shadowing in dynamical systems
• Shadowing is generic
• Approximate and real trajectories for generic dynamical systems
• The simplest shadowing
• Hyperbolic homeomorphisms and bishadowing
• The conjugacy between Cascades generated by a weakly nonlinear system and the Euler method of a flow
• Approximation by superpositions of a sigmoidal function
• Dynamical properties of learning process of weakly nonlinear and nonlinear neurons
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item