Machine Learning
ES 335 · IIT Gandhinagar · Semester II, 2023–24
ES 335 is an introduction to machine learning: decision trees and ensembles, linear and logistic regression, gradient descent, neural networks and CNNs, nearest neighbours, unsupervised and reinforcement learning, and support vector machines. Most lectures link their slides, a full class recording and notebooks.
- Instructor
- Prof. Nipun Batra
- Office
- 13/401C (directions)
- nipun.batra@iitgn.ac.in
- Lectures
- Monday and Wednesday, 8:30–10:00 am, Room 10/103
- Tutorials
- Friday, 11:30 am–1:00 pm, Room 10/103
- Teaching assistants
- 10 TAs
- Prerequisite test
- Open-book test, due 6 January 2024, 9 pm
- Recordings
- YouTube playlist
This offering ran from January to April 2024. Its slides, notebooks and class recordings remain available.
- Lectures
- 35
- Notebooks
- 50
- Recordings
- Playlist
- Quizzes
- 4, best 3 count
Lectures
- 1–2Foundations2 lectures
- 3–7Trees, model fit and ensembles5 lectures
- 8–17Linear models and optimisation10 lectures
- 18–26Classification and neural networks9 lectures
- 27–30Neighbours, unsupervised and reinforcement learning4 lectures
- 31–35Support vector machines5 lectures
Questions
Is there a project?
Not a separate one. Each assignment has a project-like question instead, the same for all students, such as building an activity classifier from public data and then from data you collect on your smartphone.
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. You must clear the prerequisite test to take the course.
What if I miss a quiz?
A missed quiz is marked zero and there are no makeups, for any reason. Only the best three of four quizzes count, which is meant for exactly this case.
Is there a mid-semester or end-semester exam?
Two of the four quizzes are held in the mid-semester and end-semester exam slots; the other two are held during the semester. All are closed book.
Can I use my laptop in class?
No. Laptops are not allowed in class for any reason.
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
- Rishiraj Adhikaryrishiraj.a@iitgn.ac.in
- Inderjeet Bhullarinderjeet.bhullar@iitgn.ac.in
- Rahul Chembakasserilrahul.chembakasseril@iitgn.ac.in
- R Yeeshu Dhurandharr.yeeshu@iitgn.ac.in
- Suraj Jaiswaljaiswalsuraj@iitgn.ac.in
- Kalash Kankariakalash.kankaria@iitgn.ac.in
- Sukruta Midigeshisukruta.midigeshi@iitgn.ac.in
- Chirag Sardachirag.sarda@iitgn.ac.in
- Ayush Shrivastavashrivastavaayush@iitgn.ac.in
- Sai Krishnaavulasaikrishna@iitgn.ac.in