Learning Objectives
The objective of the course is to equip the student to recognize and solve modern machine learning problems those arise in practical applications.
Learning Outcome
At the end of this course students will be able to implement and use some of the state-of-the-art techniques of machine learning. They will be able to compare pros and cons of various methods in terms of using them to solve some real world problems. Students will be able to analyse the complexity of an optimization problem and its solution.
Course Content
Hierarchical Bayesian models: generative models, Topic models, Bayesian nonparametrics [12 lectures]
Deep learning, artificial neural networks [7 lectures]
Distributed Computing : parallel programming and Map-reduce framework, High Performance Computing. [4 lectures]
Sequential learning: Bayesian sequential learning, stochastic gradient descent [3 lectures]
Kernel Learning, multi view spatio-temporal learning, structure prediction [12 lectures]
Privacy-aware learning [4 lectures]
Textbooks
-
Ian Goodfellow, Yoshua Bengio and Aaron Courville. Deep Learning. The MIT Press, 2016. ISBN-13: 978-0262035613.
-
Dimitri P. Bertsekas and J. Tsitsiklis. Parallel and Distributed Computation, Athena Scientific. 2015. ISBN 1-886529-15-9.
-
Christopher Bishop. Pattern Recognition and Machine Learning. Springer. 2006. ISBN-13 978-0-387-31073-2.
References
-
Bernhard Schölkopf and Alexander J. Smola. Learning with Kernel. The MIT Press 2001 ISBN: 978-0262253437
-
Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine Learning 3, no. 1 (2011): 1-122.
-
Neal Parikh and Stephen Boyd. Proximal algorithms. Foundations and Trends® in Optimization 1, no. 3 (2014): 127-239.
-
Yu Nesterov . Introductory lectures on convex programming volume I: Basic course. Lecture notes (1998).
Past Offerings
- Offered in July-Dec, 2018 by Sahely, Mrinal
Course Metadata
| Item | Details |
|---|---|
| Course Title | Topics in Machine Learning |
| Course Code | CS5001 |
| Course Credits | 3-0-0-3 |
| Course Category | ERC |
| Approved on | Senate of IIT Palakkad |