Machine Learning
ES 654 · IIT Gandhinagar · Semester II, 2022–23
ES 654 is an introduction to machine learning: decision trees and ensembles, bias and variance, linear and logistic regression with gradient descent, neural networks and CNNs, naive Bayes, nearest neighbours, clustering and support vector machines. Every lecture links its slides, and most link worked notebooks.
- Instructor
- Prof. Nipun Batra
- nipun.batra@iitgn.ac.in
- Classes
- Tuesday and Thursday, 3:30–4:50 pm IST
- Venue
- Room 1/101
- Teaching assistants
- 9 TAs
- Prerequisite test
- Open-book test, required to take the course
- Discussion
- Course Slack
This offering ran from January to April 2023. Its lecture slides, notebooks and quiz papers remain available.
- Lectures
- 29
- Notebooks
- 36
- Quiz papers
- 5
- Assignment
- Assignment 5 brief
Lectures
- 1–2Foundations2 lectures
- 3–7Trees, model fit and ensembles5 lectures
- 8–17Linear models and optimisation10 lectures
- 18–23Neural networks6 lectures
- 24–26Naive Bayes, neighbours and clustering3 lectures
- 27–29Support vector machines3 lectures
Questions
What are the prerequisites?
There are no formal prerequisites, but you are expected to know Python programming and data structures (ES 242 or equivalent), probability and statistics, linear algebra and calculus. The prerequisite test checks these.
What if I do not clear the prerequisite test?
You will not be allowed to take the course. The instructor sets the cut-off, which is not revealed in advance.
What if I miss a quiz?
A missed quiz is marked zero, for any reason. Only the best six of eight quizzes count, which is meant for exactly this case.
Is there a mid-semester or end-semester exam?
No. There are eight quizzes of equal weight, some of which may be held in the exam slot. They are closed book, and may contain both multiple-choice and written questions.
How are assignments evaluated?
Each assignment is followed by a viva. Marks are split between code that runs correctly, your understanding of the code, code quality and theory. See Assignment marks.
Is there a project?
No, there is no project component in the course.
All questions · or ask on the course Slack.
References
Reference textbooks:
- Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani, An Introduction to Statistical Learning with Applications in R (online edition)
- Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006 (free PDF)
- Jerome Friedman, Trevor Hastie and Robert Tibshirani, The Elements of Statistical Learning, Springer, 2001 (free PDF)
- Richard O. Duda, Peter E. Hart and David G. Stork, Pattern Classification, John Wiley & Sons
- Tom M. Mitchell, Machine Learning, McGraw Hill, 1997
- Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press
- Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016 (online edition)
Preparation material, to refresh the prerequisites before the course begins:
- Python Data Science Handbook, chapters 1 to 4
- Linear Algebra for Machine Learning
- Khan Academy: Statistics and Probability
Other courses:
- NPTEL Machine Learning, Balaraman Ravindran
- CMU Machine Learning, Tom Mitchell and Maria-Florina Balcan
- Coursera Machine Learning, Andrew Ng
- fast.ai Machine Learning and Practical Deep Learning for Coders
- UCI Machine Learning, Alex Ihler
Teaching assistants
- Zeel B Patel
- Shriraj Sawant
- Shrutimoy
- Sarth Dubey
- Hitarth Gandhi
- Saagar Parikh
- Eshan Gujarathi
- Gautam Vashishta
- Aadesh Desai