Weak Adversarial Networks: a novel physics-informed machine learning approach for solving high-dimensional PDEs
The Structure of WAN
Posts by Collection
portfolio
PSP-GEN: Stochastic inversion of the Process–Structure–Property chain in materials design through deep, generative probabilistic modeling
The PSP-GEN framework
DGenNO: a novel physics-aware neural operator for solving forward and inverse PDE problems based on deep, generative probabilistic modeling
The DGenNO framework
publications
A jump stochastic differential equation approach for influence prediction on heterogenous networks
Published in Communications in Mathematical Sciences 18.8 (2020), 2020
Weak adversarial networks for high-dimensional partial differential equations
Published in Journal of Computational Physics 411 (2020): 109409, 2020
Numerical solution of inverse problems by weak adversarial networks
Published in Inverse Problems 36.11 (2020): 115003, 2020
Uncertainty-driven spiral trajectory for robotic peg-in-hole assembly
Published in IEEE Robotics and Automation Letters 7.3 (2022): 6661-6668, 2022
A machine learning enhanced algorithm for the optimal landing problem
Published in Mathematical and Scientific Machine Learning. PMLR, 2022, 2022
Particlewnn: A Weak-From Deep Learning Framework for Solving Partial Differential Equations and Inverse Problems
Published in arxiv.org, 2023
Weak neural variational inference for solving bayesian inverse problems without forward models: applications in elastography
Published in Computer Methods in Applied Mechanics and Engineering 433 (2025): 117493, 2024
PSP-GEN: Stochastic inversion of the Process–Structure–Property chain in materials design through deep, generative probabilistic modeling
Published in Acta Materialia 284 (2025): 120600, 2024
Solving optimal control problems of rigid-body dynamics with collisions using the hybrid minimum principle
Published in Communications in Nonlinear Science and Numerical Simulation 143 (2025): 108603, 2025
DGenNO: a novel physics-aware neural operator for solving forward and inverse PDE problems based on deep, generative probabilistic modeling
Published in Journal of Computational Physics 538 (2025): 114137, 2025
Design-GenNO: A Physics-Informed Generative Model with Neural Operators for Inverse Microstructure Design
Published in arxiv.org, 2025
talks
“Weak Adversarial Networks: A Deep Learning Framework for Solving High-Dimensional Inverse Problems”
Published:
“Weak Adversarial Networks: A Deep Learning Framework for Solving High-Dimensional Inverse Problems”
Published:
“Deep Generative Modeling for Computational Mechanics: Inverse Design and PDE-Based Simulations”
Published:
teaching
Deep Learning for PDEs in Engineering Physics
Graduate Course, TUM, School of Engineering and Design, 2025
Lecturer: Yaohua Zang & Scholz Vincent