Dynamical properties of a perceptron learning process: structural stability under numerics and shadowing

DOI10.1007/S00332-011-9094-1MaRDI QIDQ652279zbMATH OpenOpenAlexWikidataFDO

Authors Andrzej Bielecki, Jerzy Ombach

Publication date 14 December 2011

Published in Journal of Nonlinear Science (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://doi.org/10.1007/s00332-011-9094-1

zbMATH Keywords

robustnessdynamical systemshadowingRunge-Kutta methodstopological conjugacyinverse shadowinggradient differential equationperceptron learning process

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Topological and differentiable equivalence, conjugacy, moduli, classification of dynamical systems (37C15) Approximate trajectories (pseudotrajectories, shadowing, etc.) in smooth dynamics (37C50) Multistep, Runge-Kutta and extrapolation methods for ordinary differential equations (65L06) Stability and convergence of numerical methods for ordinary differential equations (65L20) Approximation methods and numerical treatment of dynamical systems (37M99) Dynamical systems in numerical analysis (37N30)

Recommendations

• Shadowing property in analysis of neural networks dynamics.
• Dynamical properties of learning process of weakly nonlinear and nonlinear neurons
• Group actions and learning for a family of automata
• A multilayer neural network. II: Stability of its learning processes
• A multilayer neural network. I: Stability of its learning process

Cites work

• scientific article; zbMATH DE number 3772598 (Why is no real title available?)
• scientific article; zbMATH DE number 750675 (Why is no real title available?)
• scientific article; zbMATH DE number 3231759 (Why is no real title available?)
• Deterministic convergence of an online gradient method for neural networks
• Dynamical properties of learning process of weakly nonlinear and nonlinear neurons
• Estimation of the Euler method error on a Riemannian manifold
• Hyperbolic homeomorphisms and bishadowing
• Shadowing in dynamical systems
• Shadowing property in analysis of neural networks dynamics.
• Structural Stability for the Euler Method
• Structural Stability of Morse--Smale Gradient-like Flows under Discretizations
• Topological conjugacy of discrete time-map and Euler discrete dynamical systems generated by a gradient flow on a two-dimensional compact manifold

Cited in

(3)

• Multi-sensitivity, syndetical sensitivity and the asymptotic average- shadowing property for continuous semi-flows
• Dynamical properties of the reaction-diffusion type model of fast synaptic transport
• Dynamical properties of learning process of weakly nonlinear and nonlinear neurons

This page was built for publication: Dynamical properties of a perceptron learning process: structural stability under numerics and shadowing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q652279)