Dynamical Systems andOptimal Control Approach to Deep Learning

Artificial neural networks and deep learning (68T07) Optimality conditions for problems involving ordinary differential equations (49K15) Mean field games and control (49N80) Multi-agent systems (93A16)

Recommendations

A mean-field optimal control formulation of deep learning
Maximum principle based algorithms for deep learning
Deep learning as optimal control problems: models and numerical methods
Machine Learning and Control Theory
Selection dynamics for deep neural networks

Cited in

(24)

Deep learning via dynamical systems: an approximation perspective
A mean-field optimal control formulation of deep learning
Deep learning approximation of diffeomorphisms via linear-control systems
Machine learning control -- taming nonlinear dynamics and turbulence
Machine learning: deepest learning as statistical data assimilation problems
Maximum principle based algorithms for deep learning
An approach to solving optimal control problems of nonlinear systems by introducing detail-reward mechanism in deep reinforcement learning
Structure-preserving deep learning
Mixing artificial and natural intelligence: from statistical mechanics to AI and back to turbulence
A proposal on machine learning via dynamical systems
Selection dynamics for deep neural networks
A projected primal-dual gradient optimal control method for deep reinforcement learning
Riddled basins of the optimal states in learning dynamical systems
Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics
Deep learning nonlinear multiscale dynamic problems using Koopman operator
Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
A measure theoretical approach to the mean-field maximum principle for training NeurODEs
Linear-quadratic stochastic delayed control and deep learning resolution
On the overfly algorithm in deep learning of neural networks
Deep learning as optimal control problems: models and numerical methods
Control on the manifolds of mappings with a view to the deep learning
Predict globally, correct locally: parallel-in-time optimization of neural networks
Substantiation of the backpropagation technique via the Hamilton-Pontryagin formalism for training nonconvex nonsmooth neural networks
Deep Learning for Posture Control Nonlinear Model System and Noise Identification

This page was built for publication: Dynamical Systems andOptimal Control Approach to Deep Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5879784)