The modern mathematics of deep learning

DOI10.1515/dmvm-2021-0074OpenAlexW4205161316MaRDI QIDQ2164389

Gitta Kutyniok, Philipp Petersen, Philipp Grohs, Julius Berner

Publication date: 15 August 2022

Published in: Mitteilungen der Deutschen Mathematiker-Vereinigung (DMV) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.04026

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (11)

Learning-informed parameter identification in nonlinear time-dependent PDEs ⋮ Mesh-informed neural networks for operator learning in finite element spaces ⋮ Neural networks in Fréchet spaces ⋮ ReLU neural networks of polynomial size for exact maximum flow computation ⋮ Optimal Reaction Coordinates: Variational Characterization and Sparse Computation ⋮ Deterministic neural networks optimization from a continuous and energy point of view ⋮ Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance ⋮ Dynamical Systems–Based Neural Networks ⋮ Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees) ⋮ Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting) ⋮ Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

This page was built for publication: The modern mathematics of deep learning