(0) Invited Book Chapters
- (with M. Liu)
Physics-preserved neural network (P^2NN) method for scalar hyperbolic partial differential equations, Introduction to Scientific Machine Learning, Cambridge University Press, in progress.
- (with M. Liu)
Self-adaptive ReLU neural network method in least-squares data fitting, Principles and Applications of Adaptive Artificial Intelligence, Chapter 11 (2024), 242-262. DOI: 10.4018/979-8-3693-0230-9.ch011.
(1) Adaptive Neural Network (ANE) Method and Approximation Theory
- (with J. Choi and M. Liu)
ReLU neural network approximation to piecewise constant functions,
arXiv:2410.16506 [math.FA].
- (with J. Chen and M. Liu)
Self-adaptive deep neural network: numerical approximation to functions and PDEs,
J. Comput. Phys., 455 (2022), 111021.
- (with M. Liu)
Adaptive two-layer ReLU neural network: II. RITZ approximation to elliptic PDEs,
Comput. Math. Appl., 113 (2022), 103-116.
- (with M. Liu and J. Chen)
Adaptive two-layer ReLU neural network: I. Best least-squares approximation,
Comput. Math. Appl., 113 (2022), 34-44.
(2) Physics-Preserved Neural Network (P^2NN) Methods
(a) Least-Squares Neural Network (LSNN) Method for Problems without Natural Minimization Principle
- (with J. Choi and M. Liu)
Least-squares neural network (LSNN) method for linear advection-reaction equation: general discontinuous interface,
arXiv:2301.06156v4[math.NA],
SIAM J. Sci. Comput., 46:4 (2024), C448-C478.
- (with J. Choi and M. Liu)
Least-squares neural network (LSNN) method for linear advection-reaction equation: non-constant jumps, Int'l J. Numer. Anal. Modeling, 21:5 (2024), 609-628.
- (with J. Chen and M. Liu)
Least-squares neural network (LSNN) method for scalar nonlinear hyperbolic conservation laws: discrete divergence operator, arXiv2110.10895v3[math.NA],
J. Comput. Appl. Math., 433 (2023) 115298.
- (with J. Chen and M. Liu)
Least-squares ReLU neural network (LSNN) method for scalar nonlinear hyperbolic conservation law,
Appl. Numer. Math., 174 (2022), 163-176.
- (with J. Chen and M. Liu)
Least-squares ReLU neural network (LSNN) method for linear advection-reaction equation,
J. Comput. Phys., 443 (2021), 110514.
- (with J. Chen, M. Liu, and X. Liu)
Deep least-squares methods: an unsupervised learning-based numerical method for solving
elliptic PDEs,
J. Comput. Phys., 420 (2020), 109707.
(b) Deep Ritz Method and Deep Dual Methods for Problems with Natural Minimization Principle
- (with M. Liu and K. Ramani)
Dual neural network (DuNN) method for elliptic partial differential equations and systems,
J. Comput. Appl. Math., 467 (2025), 116596.
- (with M. Liu and K. Ramani)
Deep Ritz method with adaptive quadrature for linear elasticity,
Comput. Methods in Appl. Mech. Eng.,
415 (2023) 116229.
- (with Z. Hao and M. Park)
Neural network method for integral fractional Laplace equations,
East Asian Journal on Applied Mathematics, 13:1 (2023), 95-118.
- (with D. Jiao and M. Liu)
Minimization formulation for neural network based solution of Maxwell's equations in frequency domain,
in the IEEE International Symposium on Antennas & Propagation, USNC-URSI Radio Science Meeting, July 10-15, 2022, Denver, USA.
- (with M. Liu and D. Jiao)
Ritz neural network (RitzNN) method for H(curl) problems,
in the Applied Computational Electromagnetics Society (ACES) Virtual Conference, August 1-5, 2021, ACES2021OL-1302.
(c) Evolving Neural Network (ENN) Method
- (with B. Hejnal)
Evolving neural network (ENN) method for one-dimensional
scalar hyperbolic conservation laws,
SIAM J. Sci. Comput., submitted, arXiv:2312.06919[math.NA]
(3) Iterative/Optimization/Training Method
- (with T. Ding, M. Liu, X. Liu, and J. Xia)
A structure-guided Gauss-Newton method for shallow ReLU neural network, submitted, arXiv:2404.05064[cs.LG]
- (with A. Dokotorova, R. Falgout, and C. Herrera)
Efficient shallow Ritz method for 1D diffusion problems, submitted. arXiv:2404.17750[math.NA]
- (with A. Dokotorova, R. Falgout, and C. Herrera)
Efficient shallow Ritz method for 1D diffusion-reaction problems
, submitted. arXiv:2404.01496[math.NA]