ES 667: Deep Learning

IIT Gandhinagar · August 2026

ES 667 develops deep-learning models from their statistical and computational foundations. The course begins with likelihood, loss functions, and multilayer networks, and proceeds to convolutional models, sequence models, Transformers, representation learning, and generative models.

Recent and upcoming classes

Date Class Material
Tuesday, 4 August 2026 Lecture 1, part I Slides
Friday, 7 August 2026 Lecture 1, part II Slides
Tuesday, 11 August 2026 Finish Lecture 1; work through the PyTorch companion notebooks Slides · Main notebook · Main Colab · Robust notebook · Robust Colab

The same Lecture 1 deck is used across these three meetings. On 11 August we will complete the remaining material and study likelihood, MLE, regression, classification, MAP, and robust observation models through executable examples.

References

There is no required textbook. Useful references include:

  • Simon J. D. Prince, Understanding Deep Learning (online edition)
  • Christopher M. Bishop and Hugh Bishop, Deep Learning: Foundations and Concepts
  • Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola, Dive into Deep Learning (online edition)