2024_ML2.md

EE698R: Advanced Topics in Machine Learning (Spring 2024)

with focus on Generative AI

Units: 3-0-0-0-9 (3 hours lecture; total 9 credits)
Class timings: TTh 17:10-18:25 (L16)
Instructor: Vipul Arora
Office hours: After the class on Tuesday and Thursday

For Registration

• Closed for UG students, still open for PG students
• For auditing the course, please email krsumit@iitk.ac.in

TAs

Name	E-mail
Sumit Kumar	krsumit@iitk.ac.in
Rahul Kodag	rkodag@iitk.ac.in
Parampreet Singh	params21@iitk.ac.in
Akanksha singh	akankss20@iitk.ac.in
Pratikhya Ranjit	pranjit@iitk.ac.in
Adhiraj Banerjee	adhiraj@iitk.ac.in
Patnana Venkataramana Manikanta	patnana@iitk.ac.in

Course Objectives:

This course aims at introducing the students to advanced topics in machine learning (ML). The main focus will be on Generative machine learning. The lectures will focus on mathematical principles, and there will be coding based assignments for implementation.

Pre-requisites:

• Basic course on machine learning (EE698V, EE603A or equivalent). Lecture videos
• Basics of Programming (ESc101 or equivalent)

The course will need a strong background in linear algebra and probability theory.

Topics:

• Deep Neural Networks
• Generative Machine Learning
  • Random sampling (Monte Carlo methods)
  • Variational Inference
  • Generative Adversarial Networks
  • Normalizing Flows
  • Diffusion Models
• Other topics of interest, such as
  • Trustworthy AI (Model calibration, confidence estimation)
  • Explainable AI (LIME, SHAP, Grad-CAM)
  • Human in the loop learning (mislabeling detection, active learning)
  • Data efficient machine learning (small data, model adaptation, semi-supervised learning)

Grading Scheme

• Quizzes/Assignments - 30%
• Mid-semester Exam – 30%
• End-semester - 40%
• Project: 10% (bonus/optional)

Minimum attendance of 80% is needed to pass the course.

Plagiarism Penalty:

As heavy as possible. Zero-tolerance policy.

References:

This course will take excerpts from some standard books on machine learning and signal processing. But it will largely be based on articles and research papers in ML and SP conferences (e.g., NeurIPS, ICML, ICLR, Interspeech, ICASSP, etc.) and journals (e.g., IEEE TASLP, JMLR, IEEE PAMI, etc.).

Books:

• "Pattern Recognition and Machine Learning", C.M. Bishop, 2nd Edition, Springer, 2011.
• "Bayesian reasoning and machine learning", D. Barber, Cambridge University Press, 2012.
• "Deep Learning", I. Goodfellow, Y, Bengio, A. Courville, MIT Press, 2016.