Samira Pakravan

pakravans90@gmail.com

I’m a PhD candidate in the Department of Mechanical Engineering at UCSB. I received my Master’s in Computer Science from New Mexico State University. My research interest is in Scientific Machine Learning. My goal is to fuse machine learning techniques with scientific computing to invent next generation numerical methods that enable real-time and high-fidelity simulations for digital twins.

Besides research, I enjoy teaching, especially fundamental courses in my field.

news

Nov 6, 2022	Our "Neuro-symbolic partial differential equation solver" paper has been accepted to the Machine Learning and the Physical Sciences workshop at NeurIPS 2022. I'm going to attend to present a poster of our work.

selected publications

NeurIPS

Neuro-symbolic partial differential equation solver

Pouria Mistani, Samira Pakravan, Rajesh Ilango, Sanjay Choudhry, and Frederic Gibou.

NeurIPS 2022 (ML4Phys)

Abs HTML PDF

We present a highly scalable strategy for developing mesh-free neuro-symbolic partial differential equation solvers from existing numerical discretizations found in scientific computing. This strategy is unique in that it can be used to efficiently train neural network surrogate models for the solution functions and the differential op- erators, while retaining the accuracy and convergence properties of state-of-the-art numerical solvers. This neural bootstrapping method is based on minimizing resid- uals of discretized differential systems on a set of random collocation points with respect to the trainable parameters of the neural network, achieving unprecedented resolution and optimal scaling for solving physical and biological systems.