A numerical study of basins of attraction of zero-finding neural nets designed using control theory

DOI10.1007/S12591-010-0068-9MaRDI QIDQ691293zbMATH OpenOpenAlexFDO

Authors Fernando A. Pazos, Amit Bhaya

Publication date 30 November 2012

Published in Differential Equations and Dynamical Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s12591-010-0068-9

zbMATH Keywords

convergencenumerical examplescontrol theoryneural networksbasins of attractionEuler's methodcontrol Liapunov functiontrajectory following methodszero finding algorithm

Mathematics Subject Classification ID

Nonlinear ordinary differential equations and systems (34A34) Attractors and repellers of smooth dynamical systems and their topological structure (37C70) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Recommendations

• Finite-time stable versions of the continuous Newton method and applications to neural networks
• Neurodynamical optimization
• A control Liapunov function approach to generalized and regularized descent methods for zero finding
• scientific article; zbMATH DE number 829792
• Probing the basins of attraction of a recurrent neural network

Cites work

• scientific article; zbMATH DE number 3485507 (Why is no real title available?)
• scientific article; zbMATH DE number 3488538 (Why is no real title available?)
• scientific article; zbMATH DE number 3490340 (Why is no real title available?)
• A Control-Theoretic Approach to the Design of Zero Finding Numerical Methods
• A dynamical approach to convex minimization coupling approximation with the steepest descent method
• Acceleration of One-step Stationary Root-finding Algorithms
• Algorithms for unconstrained optimization problems via control theory
• Control Perspectives on Numerical Algorithms and Matrix Problems
• Evolutionary operators in global optimization with dynamic search trajectories
• On the role of singularities in Branin's method from dynamic and continuation perspectives.
• Optimally controlled iterative schemes for obtaining the solution of a non-linear equation†
• Regularized Lotka-Volterra dynamical system as continuous proximal-like method in optimization.
• The Continuous Newton--Raphson Method Can Look Ahead
• Weak singularities and the continuous Newton method
• Widely Convergent Method for Finding Multiple Solutions of Simultaneous Nonlinear Equations

Cited in

(2)

• A control Liapunov function approach to generalized and regularized descent methods for zero finding
• Finite-time stable versions of the continuous Newton method and applications to neural networks

This page was built for publication: A numerical study of basins of attraction of zero-finding neural nets designed using control theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q691293)