ES 335: Machine learning

August 2025 · IIT Gandhinagar

An introduction to machine learning: how models learn from data, how to evaluate them honestly, and the main families of methods, from decision trees and linear models to neural networks, clustering and support vector machines. Every lecture's slides, notebooks, cheat sheet and short videos are in the lecture library.

Announcements and discussion are on the course Slack: join the ES 335 workspace.

NoteCourse information

Instructor: Prof. Nipun Batra
Email: nipun.batra@iitgn.ac.in
Office: 13/401C
Directions to office

Venue: Room 10/103

Teaching Assistants:

  • Palak Gupta (palak.gupta@iitgn.ac.in)
  • Abhyudaya Nair (abhyudaya.nair@iitgn.ac.in)
  • Dekka Muni Kumar (muni.kumar@iitgn.ac.in)
  • Diya Ashvinsinh Thakor (diya.thakor@iitgn.ac.in)
  • Vinayak Rana (vinayak.rana@iitgn.ac.in)
  • Rishabh Mondal (rishabh.mondal@iitgn.ac.in)
  • Ayush Shrivastava (shrivastavaayush@iitgn.ac.in)
  • Kaloori Shiva Prasad (kaloori.shiva@iitgn.ac.in)
  • Suruchi Hardaha (suruchi.hardaha@iitgn.ac.in)
  • Prathamesh Shanbhag (prathamesh.shanbhag@iitgn.ac.in)
  • Aditya Mehta (aditya.mehta@iitgn.ac.in)
  • Guntas Singh Saran (guntassingh.saran@iitgn.ac.in)
  • Neerja Kasture (neerja.kasture@iitgn.ac.in)
  • Akash Gupta (akash.gupta@iitgn.ac.in)
  • Umang Shikarvar (umang.shikarvar@iitgn.ac.in)
  • Venkatakrishnan E (venkatakrishnan.e@iitgn.ac.in)
WarningPrerequisite exam

Submit the prerequisite exam by August 10th, 2025 at 10:00 PM.

  • It is open book and open internet.
  • Submission instructions are in the exam.
  • It is required to enrol in the course.

Prerequisites

You should be comfortable with:

  • Python programming, with good experience of data structures and algorithms
  • Probability and statistics: basic concepts and distributions
  • Linear algebra: vectors, matrices and their operations
  • Calculus: derivatives and basic optimisation

Preparation material

To refresh these before the course begins:

Reference textbooks

Primary references:

  1. Mathematics for Machine Learning, Deisenroth, Faisal and Ong. Free PDF
  2. An Introduction to Statistical Learning, James, Witten, Hastie and Tibshirani. Free online
  3. Pattern Recognition and Machine Learning, Christopher Bishop. Free PDF

Additional references:

  1. The Elements of Statistical Learning, Friedman, Hastie and Tibshirani. Free PDF
  2. Deep Learning, Goodfellow, Bengio and Courville. Free online
  3. Pattern Classification, Duda, Hart and Stork
  4. Machine Learning, Tom Mitchell
  5. Machine Learning: A Probabilistic Perspective, Kevin Murphy

Other courses