Prof. Ananth offers the following courses in the Department of Chemical Engineering at IISc:
Machine Learning for Materials and Molecules (CH 251):
(January 2023)
Introduction to data science and machine learning, examples of supervised/unsupervised/reinforcement learning, motivation behind modeling materials and molecules with examples from sustainable energy conversion, clean water/air, and human health; introduction to Python, scientific computing packages (NumPy, SciPy, Matplotlib), and simple ML packages (Scikit-learn, RDKit, DeepChem); linear and nonlinear regression, confidence intervals and goodness of fit, loss functions, gradient descent algorithm, overfitting/underfitting, regression/classification learning; clustering, singular-value decomposition, and principal component analysis; decision trees and ensemble methods, boosting and bagging techniques, random forests, gradient-boosted machine learning, hyperparameter tuning; introduction to neural networks and deep learning; introduction to neural network potentials; cheminformatics, graph and featurized representations of materials, molecules, and nanopores, and their applications in materials/molecular discovery; application of machine learning in predicting molecular/materials properties.
Engineering Mathematics (CH 201):
with Prof. Prabhu Nott (August 2020/22-23), Prof. K. Ganapathy Ayappa (August 2021)
Linear algebraic equations, linear operators including matrix, differential, and integral operators, vector and function spaces, metric and normed spaces, inner products and adjoint operators, Gram-Schmidt orthogonalization, existence and uniqueness of solutions, eigenvalues and eigenvectors/functions, Jordan forms, application to linear ODEs and Sturm-Liouville problems, PDEs and their classification, initial and boundary value problems, separation of variables in Cartesian, cylindrical, and spherical coordinates, Euler, Airy, Bessel, Legendre, Laguerre, and Chebyshev equations, similarity solutions, Taylor and Frobenius series solutions of ODEs.
Introduction to Molecular Simulations (CH 247):
with Prof. Sudeep Punnathanam (January 2021-22)
Basic statistical thermodynamics, classical simulation basics including periodic boundary conditions, cutoffs, and minimum image convention, computing potential energies and long-range corrections, Monte Carlo integration and importance sampling, Metropolis algorithm, MC ensembles, property calculation including pressure, diffusion coefficient, and radial distribution functions, molecular dynamics simulations, Lagrangian and Hamiltonian equations of motion, thermostats and barostats, time-integration algorithms, holonomic constraints, Ewald summation, basic quantum mechanics and density functional theory, Hohenberg-Kohn theorems and Kohn-Sham DFT, exchange-correlation functionals, basis sets, pseudopotentials, k-point sampling, geometry optimization, normal mode calculations, introduction to Hubbard-corrected DFT.