1 code implementation • 6 Dec 2023 • Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, Joshua Shao Zheng Low, My Ha Dao, Yew-Soon Ong
Physics-informed neural networks (PINNs) are at the forefront of scientific machine learning, making possible the creation of machine intelligence that is cognizant of physical laws and able to accurately simulate them.
no code implementations • 3 Feb 2023 • Jian Cheng Wong, Pao-Hsiung Chiu, Chinchun Ooi, My Ha Dao, Yew-Soon Ong
On the other hand, if the samples are too sparse, existing PINNs tend to overfit the near boundary region, leading to incorrect solution.
no code implementations • 15 Dec 2022 • Nicholas Sung Wei Yong, Jian Cheng Wong, Pao-Hsiung Chiu, Abhishek Gupta, Chinchun Ooi, Yew-Soon Ong
Hence, neuroevolution algorithms, with their superior global search capacity, may be a better choice for PINNs relative to gradient descent methods.
no code implementations • 24 Nov 2022 • Jordon Kho, Winston Koh, Jian Cheng Wong, Pao-Hsiung Chiu, Chin Chun Ooi
Thus, we investigate the use of physics-informed neural networks as a tool to infer key parameters in reaction-diffusion systems in the steady-state for scientific discovery or design.
no code implementations • 22 Nov 2022 • Jian Cheng Wong, Pao-Hsiung Chiu, Chin Chun Ooi, My Ha Da
Physics-Informed Neural Networks (PINNs) have been shown to be an effective way of incorporating physics-based domain knowledge into neural network models for many important real-world systems.
no code implementations • 29 Oct 2021 • Pao-Hsiung Chiu, Jian Cheng Wong, Chinchun Ooi, My Ha Dao, Yew-Soon Ong
In this study, novel physics-informed neural network (PINN) methods for coupling neighboring support points and their derivative terms which are obtained by automatic differentiation (AD), are proposed to allow efficient training with improved accuracy.
no code implementations • 11 May 2021 • Quang Tuyen Le, Pao-Hsiung Chiu, Chin Chun Ooi
The surrogate model is fast, easy to set-up and can be used to predict and assess the flow velocity and pressure fields across the domain for new designs of interest via the input of a geometry-encoding matrix.
no code implementations • 5 May 2021 • Jian Cheng Wong, Chinchun Ooi, Pao-Hsiung Chiu, My Ha Dao
In addition, we propose a novel transfer optimization scheme for use in such surrogate modeling scenarios and demonstrate an approximately 3x improvement in speed to convergence and an order of magnitude improvement in predictive performance over conventional Xavier initialization for training of new scenarios.