CS 726: Advanced Machine Learning (Spring 2022)
Lecture Schedule Slot 9, Mon-Thurs 3:30pm to 5:00pm.
Venue msteams
Instructor: Sunita Sarawagi
TAs: Prathamesh Deshpande, N Lokesh, Keshav Agarwal, Tathagat Verma
Email to reach all TAs and Instructor CS726@googlegroups.com.
For questions of general interest to the class, use moodle.
Instructor's office hours 7pm to 7:30pm on Mondays and Thursdays. Send me an email if you plan to avail of the office hours.
Syllabus and week-wise calendar: Click here
Homeworks Click here
Course description
This course will concentrate on modeling, generation, and prediction of multiple inter-dependent variables. The topics covered will span probabilistics graphical models (directed and undirected), inference methods like junction trees, belief propagation, and other approximate methods, MCMC sampling methods like Gibbs and Langevin, generative models like variational auto-encoders, GANs, Deep Gaussian processes, neural architectures for structured predictions, neural density estimation methods, causality, and other recent topics in machine learning. When appropriate the techniques will be linked to applications in NLP, speed recognition, vision, graphics, and sciences.
Eligibility
The
course is open to PhD, Masters, DD and BTech students provided they
have taken an introductory course in IITB in machine learning (listed below) and
obtained at least a BC grade in it.
Prerequisites
A
formal introductory ML course like CS 725 or CS 337 or CS 419 or DS 303 is
required. Online ML courses do not qualify as pre-requisites.
The course assumes basic knowledge of probability, statistics, and
linear algebra. Chapters 2 and 3 of
the Deep-learning
book are a good place to refresh the necessary required
background. Also, the course assumes basic background in machine
learning, for example as covered in Chapter 5 of
the Deep-learning
book and deep learning, for example, as covered in Chapter 6
of the same book. Further, we will assume that students are
familiar with CNNs, RNNs, and sequence to sequence learning with
attention.
Credit/Audit Requirements
Approximate credit structure
- 15% In-class Quizzes
- 10% Graded homeworks
- 25% Mid-semester exam
- 35% End semester exam
- 15% Project
Reading List
Primary text books
Probabilistic Graphical Models: Principles and Techniques,
by Daphne Koller and Nir Friedman, MIT Press, 2009.
Deep Learning
by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press, 2016.
The course calendar will provide links
to other relevant papers and book chapters for specific topics.
Other relevant text books:
-
A Primer on neural networks for natural language processing, by Yaov Goldbeg.
- R. G. Cowell, A. P. Dawid, S. L. Lauritzen and D. J.
Spiegelhalter. "Probabilistic Networks and Expert Systems".
Springer-Verlag. 1999.
-
M. I. Jordan (ed). "Learning in Graphical Models". MIT Press. 1998.
Collection of papers. These appear collated here.
-
J. Pearl. "Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference." Morgan Kaufmann. 1988.
- Graphical models by Lauritzen, Oxford science publications
- F. V. Jensen. "Bayesian Networks and Decision Graphs". Springer. 2001.
- Neural Networks and Deep Learning by Michael Nilson
Online courses on deep learning