Dynamical Systems andOptimal Control Approach to Deep Learning

DOI10.1017/9781009025096.011OpenAlexW4310348256MaRDI QIDQ5879784FDOQ5879784

Authors: Jiequn Han, Qianxiao Li, Weinan E 

Publication date: 6 March 2023

Full work available at URL: https://doi.org/10.1017/9781009025096.011

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

Mathematics Subject Classification ID

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)

Cited In (21)

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

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)