A proposal on machine learning via dynamical systems
From MaRDI portal
Publication:2401491
DOI10.1007/s40304-017-0103-zzbMath1380.37154OpenAlexW2600297185MaRDI QIDQ2401491
Publication date: 1 September 2017
Published in: Communications in Mathematics and Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s40304-017-0103-z
Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Applications of dynamical systems (37N99)
Related Items
Turnpike in Lipschitz—nonlinear optimal control, Interpolation and approximation via momentum ResNets and neural ODEs, EnResNet: ResNets Ensemble via the Feynman--Kac Formalism for Adversarial Defense and Beyond, Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs, Stability of Deep Neural Networks via Discrete Rough Paths, The Continuous Formulation of Shallow Neural Networks as Wasserstein-Type Gradient Flows, Structure-preserving neural networks, Turnpike in optimal control of PDEs, ResNets, and beyond, Path-Based Divergence Rates and Lagrangian Uncertainty in Stochastic Flows, ODE-RU: a dynamical system view on recurrent neural networks, Learning non-Markovian physics from data, Machine learning from a continuous viewpoint. I, Challenges in optimization with complex PDE-systems. Abstracts from the workshop held February 14--20, 2021 (hybrid meeting), Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations, Adaptive deep density approximation for Fokker-Planck equations, Revealing hidden dynamics from time-series data by ODENet, Stochastic asymptotical regularization for linear inverse problems, A Neural Network Approach to Sampling Based Learning Control for Quantum System with Uncertainty, Modelling spatiotemporal dynamics from Earth observation data with neural differential equations, A Symplectic Based Neural Network Algorithm for Quantum Controls under Uncertainty, Personalized Algorithm Generation: A Case Study in Learning ODE Integrators, A framework for randomized time-splitting in linear-quadratic optimal control, slimTrain---A Stochastic Approximation Method for Training Separable Deep Neural Networks, Physics and equality constrained artificial neural networks: application to forward and inverse problems with multi-fidelity data fusion, Large Sample Mean-Field Stochastic Optimization, Deep Neural Networks and PIDE Discretizations, Simultaneous neural network approximation for smooth functions, Physics-incorporated convolutional recurrent neural networks for source identification and forecasting of dynamical systems, A-WPINN algorithm for the data-driven vector-soliton solutions and parameter discovery of general coupled nonlinear equations, Approximation capabilities of measure-preserving neural networks, Deep limits of residual neural networks, A physics-constrained deep residual network for solving the sine-Gordon equation, Multilevel Objective-Function-Free Optimization with an Application to Neural Networks Training, Neural networks in Fréchet spaces, Dual non-autonomous deep convolutional neural network for image denoising, Deep neural networks on diffeomorphism groups for optimal shape reparametrization, Locally-symplectic neural networks for learning volume-preserving dynamics, Extension of dynamic mode decomposition for dynamic systems with incomplete information based on t-model of optimal prediction, Deep learning approximation of diffeomorphisms via linear-control systems, Sparsity in long-time control of neural ODEs, Accuracy and architecture studies of residual neural network method for ordinary differential equations, Data-driven vortex solitons and parameter discovery of 2D generalized nonlinear Schrödinger equations with a \(\mathcal{PT}\)-symmetric optical lattice, Globally Convergent Multilevel Training of Deep Residual Networks, Neural ODE Control for Classification, Approximation, and Transport, A mathematical perspective of machine learning, Adaptive task decomposition physics-informed neural networks, Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs, Unnamed Item, An ODE-based neural network with Bayesian optimization, A functional approach to interpreting the role of the adjoint equation in machine learning, Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons, Neural integration for constitutive equations using small data, A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms, Universal approximation on metric spaces, PDE-based group equivariant convolutional neural networks, The Mori-Zwanzig formulation of deep learning, Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs, Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems, Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning, Mini-workshop: Analysis of data-driven optimal control. Abstracts from the mini-workshop held May 9--15, 2021 (hybrid meeting), Unnamed Item, Data-driven optimal control of a SEIR model for COVID-19, Methods to recover unknown processes in partial differential equations using data, A review on deep learning in medical image reconstruction, Deep learning of dynamics and signal-noise decomposition with time-stepping constraints, PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network, Structure-Preserving Method for Reconstructing Unknown Hamiltonian Systems From Trajectory Data, Discovery of Dynamics Using Linear Multistep Methods, The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems, Forward stability of ResNet and its variants, Deep neural networks motivated by partial differential equations, Residual networks as flows of diffeomorphisms, Variational networks: an optimal control approach to early stopping variational methods for image restoration, Unnamed Item, Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection, Selection dynamics for deep neural networks, Unnamed Item, Deep learning of thermodynamics-aware reduced-order models from data, Learning adaptive regularization for image labeling using geometric assignment, Continuous-time system identification with neural networks: model structures and fitting criteria, Gradient convergence of deep learning-based numerical methods for BSDEs, Deep learning as optimal control problems: models and numerical methods, Model reduction and neural networks for parametric PDEs, The Random Feature Model for Input-Output Maps between Banach Spaces, Classification with Runge-Kutta networks and feature space augmentation, MgNet: a unified framework of multigrid and convolutional neural network, A mean-field optimal control formulation of deep learning, Quantized convolutional neural networks through the lens of partial differential equations, Geometric numerical integration of the assignment flow, Shared Prior Learning of Energy-Based Models for Image Reconstruction, Structure-preserving deep learning, Continuous-domain assignment flows, Probabilistic solutions to DAEs learning from physical data, A measure theoretical approach to the mean-field maximum principle for training NeurODEs, Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning, Do ideas have shape? Idea registration as the continuous limit of artificial neural networks, Optimization with learning-informed differential equation constraints and its applications, A deep domain decomposition method based on Fourier features, Layer-Parallel Training of Deep Residual Neural Networks, SPADE4: sparsity and delay embedding based forecasting of epidemics, Deep neural network based adaptive learning for switched systems, Deep learning via dynamical systems: an approximation perspective, Learning Hamiltonian systems with mono-implicit Runge-Kutta methods, Pricing options on flow forwards by neural networks in a Hilbert space, Dynamical Systems–Based Neural Networks, Control of neural transport for normalising flows, Optimal control using to approximate probability distribution of observation set, Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks, Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics, On mathematical modeling in image reconstruction and beyond
Uses Software
Cites Work
