[HTML][HTML] Integrating machine learning with human knowledge

C Deng, X Ji, C Rainey, J Zhang, W Lu - Iscience, 2020 - cell.com
Machine learning has been heavily researched and widely used in many disciplines.
However, achieving high accuracy requires a large amount of data that is sometimes …

Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning

E Weinan, J Han, A Jentzen - Nonlinearity, 2021 - iopscience.iop.org
In recent years, tremendous progress has been made on numerical algorithms for solving
partial differential equations (PDEs) in a very high dimension, using ideas from either …

Deep splitting method for parabolic PDEs

C Beck, S Becker, P Cheridito, A Jentzen… - SIAM Journal on Scientific …, 2021 - SIAM
In this paper, we introduce a numerical method for nonlinear parabolic partial differential
equations (PDEs) that combines operator splitting with deep learning. It divides the PDE …

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

C Beck, F Hornung, M Hutzenthaler… - Journal of Numerical …, 2020 - degruyter.com
One of the most challenging problems in applied mathematics is the approximate solution of
nonlinear partial differential equations (PDEs) in high dimensions. Standard deterministic …

[책][B] Traffic congestion control by PDE backstep**

H Yu, M Krstic - 2022 - Springer
This book explores the development of PDE (partial differential equation) backstep**
controllers for the suppression of stop-and-go instabilities and oscillations in congested …

Deep reinforcement learning for adaptive mesh refinement

C Foucart, A Charous, PFJ Lermusiaux - Journal of Computational Physics, 2023 - Elsevier
Finite element discretizations of problems in computational physics often rely on adaptive
mesh refinement (AMR) to preferentially resolve regions containing important features …

Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities

M Hutzenthaler, A Jentzen, T Kruse - Foundations of Computational …, 2022 - Springer
Partial differential equations (PDEs) are a fundamental tool in the modeling of many real-
world phenomena. In a number of such real-world phenomena the PDEs under …

Iterative value-aware model learning

A Farahmand - Advances in Neural Information Processing …, 2018 - proceedings.neurips.cc
This paper introduces a model-based reinforcement learning (MBRL) framework that
incorporates the underlying decision problem in learning the transition model of the …

Space-time error estimates for deep neural network approximations for differential equations

P Grohs, F Hornung, A Jentzen… - Advances in …, 2023 - Springer
Over the last few years deep artificial neural networks (ANNs) have very successfully been
used in numerical simulations for a wide variety of computational problems including …

Exploiting the flexibility inside park-level commercial buildings considering heat transfer time delay: A memory-augmented deep reinforcement learning approach

H Zhao, B Wang, H Liu, H Sun, Z Pan… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The energy consumed by commercial buildings for heating and cooling is significantly
increased. To better cope with the uncertainty introduced by the high penetration of …