ES 667 · Deep Learning

IIT Gandhinagar · August 2026 · Prof. Nipun Batra

This site contains the lecture materials for ES 667. Course dates, grading, and announcements are on the August 2026 course page.

Current material

Lecture 1 · Where Deep Learning Losses Come From

• Slides (PDF)
• Companion notebook (HTML)
• Companion notebook (Colab)
• Notebook source (IPYNB)
• Robust regression notebook (HTML)
• Robust regression notebook (Colab)
• Robust regression source (IPYNB)

The main notebook uses torch.distributions to work through probability mass and density, i.i.d. observations, maximum likelihood, linear regression, binary classification, and MAP estimation. The shorter robust-regression notebook compares Gaussian/MSE, Laplace/MAE, and Student-t observation models on the same data.

Course materials

• Lecture decks
• Notebooks
• Assignments
• Course guide
• References

Questions and announcements are handled in the course Slack workspace.