Pre-Conference Workshop – CASML 2024
About
The pre-conference workshop aims to upskill people from academia and industry by providing hands-on training experience on Scientific ML techniques like Physics Informed Neural Networks (PINNs), Neural Operators, etc. The workshop will have lecture sessions and hands-on sessions. The pre-conference workshop will be for 2 days from 14-15 December, happening at the Department of Computational and Data Sciences, at the Indian Institute of Science.
Schedule
| Time | Day 1 (14 Dec) | Day 2 (15 Dec) |
|---|---|---|
| Morning Session 1 | Lecture on PINNs | Variational PINNs – Introduction to FastVPINNs |
| Morning Session 2 | Hands-on Session on building PINNs from scratch | Hands-on session in Variational PINNs |
| Afternoon Session 1 | PINNs for fluid flow problems | Lecture on Neural Operators |
| Afternoon Session 2 | Hands-on session for fluid flow problems in PINNs | Hands-on session with Neural Operators |
Registration
Participants who have successfully registered for the conference and have paid the registration fees are eligible to attend the free pre-conference workshop.
Venue
Room 102, Department of Computational and Data Sciences at Indian Institute of Science.
Important Notes
- Participants are required to bring their own computing devices such as laptops. We will not be providing them.
- Registration for the conference is mandatory to attend the workshop.
Organizing Committee
Prof. Sashikumaar Ganesan
Professor
Department of Computational and Data Sciences, IISc Bangalore
Convenor, AIREX Lab
Founder and CAiO, Zenteiq AiTech Innovations Private Limited
Research Interests: SciML, Parallel Computing, AI-driven Digital Twin
HomePage
Thivin Anandh
PhD Student
Department of Computational and Data Sciences, Indian Institute of Science, Bangalore
Research Interests: High Performance Computing, Scientific Machine Learning, PINNs for CFD
HomePage
Divij Ghose
Senior Research Fellow
Department of Computational and Data Sciences, Indian Institute of Science, Bangalore
Research Interests: Physics informed Neural Networks, Uncertainty quantification
HomePage