I’m Nima, a Computer Science PhD student at the University of Western Ontario exploring deep learning applications in scientific computing, particularly for solving partial differential equations (PDEs) with Physics Informed Neural Networks (PINNs) and Neural Operators. Currently, I’m working on designing transfer learning methods to make knowledge transferable between physical domains. Outside of research, I enjoy hitting the trails on my mountain bike or unwinding with video games.

Publications

[1] Nima Hosseini Dashtbayaz, Ghazal Farhani, Boyu Wang, and Charles Ling. “Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations,” International Joint Conference on Artificial Intelligence (IJCAI), 2024 (arXiv)

Projects

• Tensorflow 2 Implementation of PINNs: Github Keras and TF2 implementation for PINNs, including Burger’s, Schrodinger’s, Pisson’s, Wave, Heat, and Advection equations so far.
• Few-shot Domain Adaptation and Cross-Domain FSL, A Survey. Part of my undergrad thesis work at Amirkabir University of Technology.

Education

• PhD in Computer Science, University of Western Ontario, Sep 2023 - Present
  • Supervisor: Prof. Boyu Wang
• MSc in Computer Science, University of Western Ontario, Sep 2022 - Aug 2023
  • Supervisor: Prof. Boyu Wang
  • Vector Scholarship in AI Recipient
  • Transferred to PhD
• BSc in Computer Science, Amirkabir University of Technology, Sep 2018 - Aug 2022
  • GPA: 4.0/4.0
  • Thesis: Few-shot Domain Adaptation and Cross-Domain Few-shot Learning, A Survey
  • Member of the students’ scientific society (math and CS) and chief editor of the Halgheh magazine (in Persian)

Contact

• Email: nhosse5@uwo.ca, nimahsnd@gmail.com
• LinkedIn: nimahsn
• Twitter: @nimahsnd
• Github: nimahsn