Talks and presentations

Reinforcement Learning: Zero to ChatGPT

March 03, 2023

I have given this talk for a Machine Learning seminar hosted by the Department of Applied Mathematics, University of Waterloo. This talk gives an introduction to reinforcement learning, proximal policy optimization (PPO), and reinforcement learning with human feedback (RLHF) used to train large language models (LLMs) such as ChatGPT.

Greg n Arsh podcast

January 06, 2023

I have been featured in a podcast with our wonderful Greg Hogg and Arsheya Jain! We had an interesting discussion about my journey into the data science and research world, and my life before that.