Research Interests
AI for science
Multimodal representation learning
Numerical linear algebra
Graph signal processing
Publications
Journal Articles
T. Fan, N. Trask, M. D’Elia and E. Darve, “Probabilistic Partition Of Unity Networks for High Dimensional Regression Problems,” International Journal for Numerical Methods in Engineering 2023, 124 (10), 2215– 2236, Jan. 2023.
T. Fan, D. I Shuman, S. Ubaru, and Y. Saad, “Spectrum-Adapted Polynomial Approximation for Matrix Functions with Applications in Graph Signal Processing,” Algorithms 2020, 13, 295, Nov. 2020.
Conference Papers
T. Fan, K. Xu, J. Pathak, and E. Darve, “Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks,” in Proceedings of the AAAI Fall 2020 Symposium on Physics-Guided AI to Accelerate Scientific Discovery, remote, Aug. 2020.
L. Fan, D. I Shuman, S. Ubaru, and Y. Saad, “Spectrum-Adapted Polynomial Approximation for Matrix Functions,” in Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, United Kingdom, May. 2019.
Presentations
Conference Presentations
“Unsupervised Learning and Dimension Reduction for Engineering Systems,” Mechanistic Machine Learning and Digital Engineering for Computational Science Engineering and Technology (MMLDE-CSET), El Paso, TX, Sep. 2023.
“A Structure Preserving Deep Learning Framework for High Dimensional Regression,” Mathematical and Scientific Machine Learning (MSML) Workshop, Providence, RI, Jun. 2023.
“Expectation-Maximizing Probabilistic Partition Of Unity Networks with Applications in Quantum Computing,” World Congress in Computational Mechanics (WCCM) & Asian Pacific Congress on Computational Mechanics (APCOM), remote, Aug. 2022.
“Solving Inverse Problems in Steady-State Navier-Stokes Equations using Physics Constrained Machine Learning,” World Congress in Computational Mechanics (WCCM) & European Community on Computational Methods in Applied Sciences (ECCOMAS), remote, Jan. 2021.
“Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks,” AAAI Fall 2020 Symposium on Physics-Guided AI to Accelerate Scientific Discovery, remote, Aug. 2020.
“Spectrum-Adapted Polynomial Approximation for Matrix Functions,” Joint Mathematics Meetings, Baltimore, MD, Jan. 2019 (Outstanding Poster Award Winner); and Graph Signal Processing Workshop, Minneapolis, MN, Jun. 2019.
“Computational Studies of Intramolecular Spiroether Synthesis from Peroxy Enolates,” Midwestern Undergraduate Computational Chemistry Conference, Champaign, IL, Aug. 2017; Midstates Consortium for Math and Science Undergraduate Research, Chicago, IL, Nov. 2017; American Chemistry Society (ACS) National Meeting & Expo, New Orleans, LA, Mar. 2018.
Other Presentations
“Probabilistic Partition Of Unity Networks for High Dimensional Regression Problems,” Berkeley/Stanford CompFest, Stanford, CA, Dec. 2022.
“A General Approach for Inverse Problems using Physics Constrained Machine Learning,” Ansys TechCon, remote, Nov. 2020.