Teaching

Deep Learning (DS4144)

August semester · 4 credits · Lecture and lab · elective

A foundational course in modern neural network architectures — convolutional networks, transformers, graph neural networks, GANs, autoencoders, diffusion models — covering both how these models are trained and how to interpret their results.

Prerequisites: familiarity with linear algebra, probability, statistics, and Python.

Suggested reading: Deep Learning: Foundations and Concepts (Christopher M. Bishop & Hugh Bishop).

Data Science Practice (DS3294)

January semester · 4 credits · Lecture and lab
[the January 2026 edition was co-taught with Kalpesh Kapoor]

A hands-on course addressing the coding-literacy gap for data science: command-line and Linux fundamentals, version control, debugging and testing, documentation, and parallel/GPU programming — the practical tooling behind doing data science, not just the theory.

Suggested reading: Data Science from Scratch (Joel Grus), Effective Python (Brett Slatkin), Clean Code in Python (Mariano Anaya).