Current Research Interests
- Up to date information about my research can be found on My Research Homepage
- Neural Operators (Learning in infinite-dimensional function spaces, as opposed to traditional neural networks that learn vector-to-vector mappings); Short Intro
- Equivariant Networks (Embedding symmetries into neural networks); Short Intro 1 ;Short Intro 2
- Participated in the NSF funded REU program “Mathematical, Statistical and Computational Methods for Problems inthe Life Sciences”.
- Designed Active Learning based Sampling to adaptively sample training examples to faster the convergence.
- Designed Self-normalized algorithm to simulate draws from unnormalized distributions.
- Compatible with 3 recent DL based PDE solvers: Deep Rits Method, Deep Galerkin Method, Weak Adversarial Networks
- Poster
- Paper
- Git Repo