Machine Learning

Instructor: Nipun Batra (nipun.batra@iitgn.ac.in)
Teaching Assistants: Indradeep (indra.mastan@iitgn.ac.in), Sudhakar (sudhakar.kumawat@iitgn.ac.in ), Supratim (supratim.shit@iitgn.ac.in), Shubham (shubam.singh@iitgn.ac.in)
Course Timings: Tue and Friday (3:30 to 5 PM in 1/101)
Office hours: Monday (12 Noon to 1): Please try to stick to this time unless it is an emergency

Pre-requisites:

Good experience in Python programming
Probability
Linear Algebra

Course preparation: Students are encouraged to study some of the following to refresh their understanding of some of the prerequisities before the course formally begins.

First four chapters of the Python Data Science handbook
Some material on Linear Algebra
Khan academy course on Stats and Probability

Reference textbooks:

Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R
Christopher Bishop. Pattern Recognition and Machine Learning. Springer, 2006.[Freely available online]
Friedman J, Hastie T, Tibshirani R. The elements of statistical learning. New York, NY, USA:: Springer series in statistics; 2001.[Freely available online]
Duda RO, Hart PE, Stork DG. Pattern classification. John Wiley & Sons; 2012 Nov 9.
Mitchell TM. Machine learning. 1997. Burr Ridge, IL: McGraw Hill. 1997;45(37):870-7.
Murphy, K. Machine Learning: A Probabilistic Perspective. MIT Press
Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016 Nov 18.[Freely available online]

Grading policy:

Project (in groups of 4 or less) (Some ideas from instructors), and some ideas from a Stanford ML course : 40%
Project proposal report (due Jan 20) : 5%
Phase-I presentation (week of Feb 10) : 5%
Phase-II presentation (week of March 15) : 5%
Final project 3 minute madness (week of April 20) [See 3MT for inspiration] : 5%
Final project demo and poster (week of April 20) : 15%
Final report (due April 22) : 5%
3 Surprise quizzes worth 3% each, best 2/3 are recorded for grade : 6%
Quiz 1 will be held before or on 15th Jan
Quiz 2 will be held before or
End semester : 10%
Paper presentation [Slides template][3 people argue for each paper. One person summarises the paper, second person acts as an advocate representing the paper; and the third person is the devil’s advocate convincing the jury that paper has flaws] : 4%
Kaggle competition : 4% [done individually, due sometime early April]
Machine Learning demo (like this or this or this or this) [Same team as project][due 30th March ] : 4%
8 Programming Homework Assignments (50% credit for late submission (upto 1 day for 1st assignment and 2 for others)) [NB - A subset of these will have an associated viva] : 32%
Bonus marks - 10 marks if you get into Master level on Kaggle or 5 marks if you get into Expert level on Kaggle

Some other ML courses

Machine Learning Spring 2019

ES 654