← Search

Seok-Bae Yun

2 accepted papers

2023

PIXEL: Physics-Informed Cell Representations for Fast and Accurate PDE Solvers

AAAI 2023technical

With the increases in computational power and advances in machine learning, data-driven learning-based methods have gained significant attention in solving PDEs. Physics-informed neural networks (PINNs) have recently emerged and succeeded in various forward and inverse PDE problems thanks to their e…

2023

Separable Physics-Informed Neural Networks

NeurIPS 2023spotlight

Physics-informed neural networks (PINNs) have recently emerged as promising data-driven PDE solvers showing encouraging results on various PDEs. However, there is a fundamental limitation of training PINNs to solve multi-dimensional PDEs and approximate very complex solution functions. The number o…