Shadowing property in analysis of neural networks dynamics.
From MaRDI portal
Publication:1426759
DOI10.1016/S0377-0427(03)00486-2zbMath1033.37044WikidataQ123956609 ScholiaQ123956609MaRDI QIDQ1426759
Jerzy Ombach, Andrzej Bielecki
Publication date: 15 March 2004
Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)
Euler methodRobustnessGradient differential equationInverse shadowingMultilayer neural network learning processShadowing
Neural biology (92C20) Dynamical systems in biology (37N25) Neural networks for/in biological studies, artificial life and related topics (92B20) Approximate trajectories (pseudotrajectories, shadowing, etc.) in smooth dynamics (37C50) Approximation methods and numerical treatment of dynamical systems (37M99)
Related Items
Dynamical properties of the reaction-diffusion type model of fast synaptic transport ⋮ Dynamical properties of a perceptron learning process: structural stability under numerics and shadowing ⋮ Unnamed Item ⋮ Properties and applications of weakly nonlinear neurons.
Cites Work
- \(\omega\)-limit sets for axiom A diffeomorphisms
- Stability theorems and hyperbolicity in dynamical systems
- Inverse shadowing by continuous methods
- Deterministic convergence of an online gradient method for neural networks
- Shadowing in dynamical systems
- Approximate and real trajectories for generic dynamical systems
- Topological conjugacy of discrete time-map and Euler discrete dynamical systems generated by a gradient flow on a two-dimensional compact manifold
- On structural stability of ordinary differential equations with respect to discretization methods
- Persistence in expansive systems
- The simplest shadowing
- Structural Stability of Morse--Smale Gradient-like Flows under Discretizations
- Hyperbolic homeomorphisms and bishadowing
- The discretized flow on domains of attraction: a structural stability result
- Topological conjugacy of cascades generated by gradient flows on the two-dimensional sphere
- On Cj-closeness between the solution flow and its numerical approximation
- 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
