Current Research Interests

• Neural PDE Solvers My Resarch Home Page
  • Neural Operators (Learning in infinite-dimensional function spaces, as opposed to traditional neural networks that learn vector-to-vector mappings)
    • Short Intro: Neural Operators
  • Physics Informed Neural Networks (Solving PDEs by penalizing the extent to which the network solution violates the PDE)
    • Sec. 1.2.2 of My Paper
    • Exemplary Notebook for Simple 2D Poisson
• Equivariance (Embedding symmetries into networks) My Resarch Home Page
  • Short Intro: Group Equivariant CNN
  • Short Intros: Euclidean GNN for Molecular Graphs, Point Clouds, etc
    • Part I Invariant GNNs and Equivariant GNNs
    • Part II Equivariant GNNs with Spherical Tensors
    • Part III Unconstrained Euclidean GNNs with Frame Averaging
• Generative Models (Learning the underlying data distribution and generate new, realistic samples that resemble the original data) My Research Home Page
  • Short Intro: Generative Models and VAE; Notebook for Simple VAE on MNIST Data

The slides will be regularly updated, with more content added over time. If you find them helpful and would like to use any of my slides, feel free to send me an email.