Computing Lyapunov functions using deep neural networks (Q2043422)

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

Computing Lyapunov functions using deep neural networks

scientific article; zbMATH DE number 7377229

Language	Label	Description	Also known as
default for all languages	No label defined
English	Computing Lyapunov functions using deep neural networks	scientific article; zbMATH DE number 7377229

Statements

instance of

scholarly article

0 references

title

Computing Lyapunov functions using deep neural networks (English)

0 references

author

Lars Grüne

0 references

published in

Journal of Computational Dynamics

0 references

publication date

2 August 2021

0 references

full work available at URL

https://arxiv.org/abs/2005.08965

0 references

zbMATH Keywords

deep neural network

0 references

Lyapunov function

0 references

stability

0 references

small-gain condition

0 references

curse of dimensionality

0 references

training algorithm

0 references

describes a project that uses

TensorFlow

0 references

DGM

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach

0 references

Advances in computational Lyapunov analysis using sum-of-squares programming

0 references

Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations

0 references

Large-scale machine learning with stochastic gradient descent

0 references

Optimization methods for large-scale machine learning

0 references

A regularization of Zubov’s equation for robust domains of attraction

0 references

Approximation by superpositions of a sigmoidal function

0 references

Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures

0 references

On a small gain theorem for ISS networks in dissipative Lyapunov form

0 references

Small gain theorems for large scale systems and construction of ISS Lyapunov functions

0 references

Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations

0 references

Computation of Lyapunov functions for nonlinear discrete time systems by linear programming

0 references

Review on computational methods for Lyapunov functions

0 references

An algorithm for constructing Lyapunov functions

0 references

Q5584086

0 references

Solving high-dimensional partial differential equations using deep learning

0 references

Multilayer feedforward networks are universal approximators

0 references

Deep backward schemes for high-dimensional nonlinear PDEs

0 references

Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations

0 references

A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations

0 references

Small-gain theorem for ISS systems and applications

0 references

A Lyapunov formulation of the nonlinear small-gain theorem for interconnected ISS systems

0 references

Q3946473

0 references

Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems

0 references

DGM: a deep learning algorithm for solving partial differential equations

0 references

Smooth stabilization implies coprime factorization

0 references

Q5724099

0 references

Identifiers

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Computing Lyapunov functions using deep neural networks