Srijit Mukherjee

Teaching

“I don’t believe I can really do without teaching. The reason is, I have to have something so that when I don’t have any ideas and I’m not getting anywhere I can say to myself, ‘At least I’m living; at least I’m doing something; I am making some contribution’ — it’s just psychological.” ~ Richard Feynman (Surely You’re Joking Mr. Feynman!)

dnn Deep Neural Networks — This course builds deep neural networks from scratch - starting from Linear and Logistic Regression, progressing through shallow to deep architectures, covering gradient computation, backpropagation, and optimization via NumPy, and culminating in the full deep learning training pipeline in PyTorch.
llm Large Language Models — This course teaches LLMs from first principles across 7 lessons — covering the mathematics of language and transformers, the deep learning training process, and building a small GPT from scratch, culminating in prompt engineering and a 3-hour LLM overview. This is dedicated to Andrej Karpathy, whose teachings have shaped my fundamentals.