Workshop - DLSC 2025
- dlsc2025@lnmiit.ac.in
About the Workshop
The workshop cum FDP is jointly organizing by CMFC, Department of Mathematics, CMLBDA in association with Indian Society for Mathematical Modeling and Computer Simulation (ISMMACS). Machine learning and deep learning techniques have gained significant popularity in recent years, particularly in the context of scientific computing. This workshop cum FDP aims to introduce participants to Machine Learning, Deep Learning, and Physics-Informed Neural Networks (PINNs), with a focus on their applications in solving ordinary and partial differential equations. Tailored for PhD students, postdoctoral researchers, and faculty members, the workshop is designed to provide both theoretical insights and practical knowledge that can be directly applied to their teaching and research.
The workshop will cover both classical methods and the latest advances in deep learning for computational mathematics. Participant young researchers and scientists will receive a foundational understanding of neural networks and hands-on training with relevant tools and libraries. The workshop provides essential tools and knowledge for cutting-edge research in deep learning for scientific computing. The workshop also highlights challenges and opportunities, focusing on how deep learning can address real-world issues in various domains such as society, the environment, fluid dynamics, meteorology, and financial markets.
Additionally, the workshop is aligned with the Artificial Intelligence mission of the GOI and aims to raise awareness of the connections between mathematics, deep learning, and real-world problems, by engaging closely with academia and industry to develop core research capability.
We are confident that this intensive five-day workshop, set in the vibrant academic environment of LNMIIT Jaipur, will provide ample opportunities for collaboration and further research development among participants and speakers.
List of Topics to be covered in the workshop:
- Essentials of Python for the workshop, Introduction to Scikit-learn, Matplotlib, Numpy, Introduction to Keras and Tensorflow or Pytorch, Hands on Session
- Basics of Machine Learning: Supervised Machine Learning; Classification and Regression Tasks and their Mathematical Interpretation, Neural Networks: Simple Perceptron Model; Multilayer Perceptron, Back propagation and Training Algorithms, Python Implementation on some benchmark Problems,
- Pre Deep Learning Era: MLP architecture for solving ODEs and PDEs with implementation in Python on some use-cases, Introduction to Deep Learning: Deep Neural networks, Stochastic gradient descent algorithms for training, different architectures: Convolutional Neural Networks, ResNets; Auto-encoders; Hands on session using Keras and Tensorflow or Pytorch
- Theoretical Foundations: Universal approximation properties of the Neural networks, Bias-Variance decomposition, Bounds on approximation and generalization errors, Introduction to Physics-Informed Neural Networks (PINNs); Automatic differentiation; Various PINN Models and their application domains. PINNs for solving Direct Problems (solution of ODEs and high dimensional PDEs), PINNs for solving inverse Problems (parameter estimation of Models; Recovery of Differential Equations from Data), Hands on session.
- Forward and Adjoint sensitivity Analysis for ODE, Neural ODE and implementation, Hands on session.
- Graph Neural Network: Building Block for Graph Neural ODE, Introduction to extreme learning machine (ELM), Application to delay differential equations, Other Scientific ML algorithms: PDENets; SiNDy, etc, Challenges and Future Directions in Scientific Machine Learning
Speakers
- Prof. B.V. Rathish Kumar, Department of Mathematics & Statistics, IIT Kanpur
- Prof. Shruti Dubey, Department of Mathematics, IIT Madras
- Prof. B.S. Panda, Department of Mathematics, IIT Delhi
- Prof. Ritesh Kumar Dubey, Department of Mathematics, SRM University, Kattankulathur
- Prof. Sanjeev Kumar, Department of Mathematics, Joint Faculty at Mehta Family School of Data Science and Artificial Intelligence, IIT Roorkee
- Prof. C.S. Sastry, Department of Mathematics and Department of Artificial Intelligence, IIT Hyderabad
- Dr. Subrat Dash, Department of Computer Science, The LNMIIT Jaipur
Target Audience
Research Scholars, Post-Doctoral Fellows, Faculty Members and other interested participants from universities, institutions, industries and R&D Organizations.