Teaching
Courses I have helped teach — from probability theory to deep reinforcement learning.
Introduction to Reinforcement Learning
Graduate-level survey of core RL theory: MDPs, dynamic programming, Monte Carlo, temporal-difference learning, policy-gradient methods, multi-armed bandits, and multi-agent RL.
View Course at UCR
Digital Image Processing
Full pipeline from sensor-level acquisition through enhancement, restoration, and compression. Labs emphasise building end-to-end image processing systems under Prof. Bir Bhanu — my own Ph.D. advisor.
View Course at UCR
Probability, Random Variables & Random Processes
Rigorous probability theory with engineering applications — random variables, distributions, stochastic processes, autocorrelation, spectral analysis, and linear systems with random inputs.
View Course at UCR
Discrete Structures
Foundations of discrete mathematics: number theory, cryptography, asymptotic notation, recurrences, counting, graph theory, and trees with emphasis on proof techniques.
View Course at UCR
Data Analysis Methods
End-to-end data analysis workflow: descriptive statistics, web data acquisition, cleaning, crowdsourcing, supervised & unsupervised learning, and visualisation with Python.
View Course at UCR