This archived page records a Spring 2022 offering at HKUST(GZ).

Course focus

The course introduced machine learning for materials science through mathematical foundations, physical modeling, and Python-based case studies. It covered neural networks, sampling and Fourier analysis, model fitting, physics-informed methods for PDEs, and machine learning for materials prediction.

Offering

Spring 2022, HKUST(GZ). The course was offered remotely through Canvas and Zoom.

Topics

• Mathematical preliminaries, sampling, and model fitting
• Neural networks, convolutional and recurrent architectures, and graph-based models
• Physics-informed learning, reduced models, and materials-science applications

References

• N. Thuerey, P. Holl, M. Mueller, P. Schnell, F. Trost, K. Um. Physics-based Deep Learning.
• I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press, 2016.
• Zhihua Zhou. Machine Learning. Tsinghua University Press, 2016.