Machine learning based fast inversion for isogeometric matrices

Picture of quanling-deng.md Quanling Deng

11 Jul 2023

This project aims to develop machine learning-based fast inversion techniques for matrices in implicit isogeometric discretizations. Implicit isogeometric discretizations are known for their accuracy and stability in solving complex time-dependent partial differential equations. However, matrix inversions in these methods can be computationally intensive. In this project, we aim to revolutionize the efficiency of matrix inversion by leveraging machine learning algorithms. Through comprehensive training and optimization, our intelligent algorithms will accelerate the inversion process, enabling faster computations in implicit isogeometric discretizations. This innovative endeavor sits at the intersection of machine learning and computational mathematics.

You are on Aboriginal land.

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

arrow-left bars search times arrow-up