ELL409: Machine Intelligence and Learning

Instructor: Seshan Srirangarajan

Lecture Timing:

Day/Time: Mon, Tue, Fri 12:00 pm - 12:50 pm (Slot J)
Room: Online

Teaching Assistants:

Abhinav Gaur (eet192237 AT ee.iitd.ac.in)
Panchal Sanket Hitendrakumar (eet192347 AT ee.iitd.ac.in)
Vidushi Jain (eet192356 AT ee.iitd.ac.in)
Srinivas Anjay Kumar Nyayapati (jtm192169 AT dbst.iitd.ac.in)
Abhilash Gaur (tiz208008 AT dbst.iitd.ac.in)

Pre-requisites: MTL106, COL106

The course is open to all suitably inclined B.Tech. students of all disciplines, who satisfy the pre-requisites listed above.

Reference Books:

  • [Bishop] Pattern Recognition and Machine Learning by C. M. Bishop, 1st Edition, 2006 (2nd Indian Reprint, 2015).
  • [Flach] Machine Learning: The Art and Science of Algorithms that Make Sense of Data by P. Flach, 1st Edition, 2012.
  • [RN_Book] Artificial Intelligence: A Modern Approach by S. Russell and P. Norvig, 3rd Edition, 2014.
  • [AML_Book] Learning from Data: A Short Course by Y. S. Abu-Mostafa, M. Magdon-Ismail, and H.-T. Lin, 1st Edition, 2012.

    Other References:

  • [Stanford_CS229] Machine Learning Course (CS229), Stanford University, Course Materials / Handouts.
  • P. Domingos, A Few Useful Things to Know about Machine Learning, Communications of the ACM, Vol. 55, No. 10, pp. 78-87, 2012.

    Course Grading:

    Minor: 30 %
    Programming Assignments: 30 %
    Major: 40 %

    Exam Schedule:

    Minor: 17 Mar 2021 (Wed)
    Major: 11 May 2021 (Tue)

    Course Outline:

    S. No. Topics Lectures References
    1. Introduction to the Course 1
    2. Basics of Learning: Learning Model, Theory of Generalisation 2-11 [AML_Book: Chap 1], [AML_Book: Chap 2]
    3. Linear Models for Regression 12, 15 [AML_Book: Chap 3]
    4. Logistic Regression 13-14 [AML_Book: Chap 3]
    5. Model Selection: Regularization, Validation 16-18 [AML_Book: Chap 4]
    6. Neural Networks 19-22 [Stanford_CS229: Deep Learning]
    7. Support Vector Machines 23 [AML_Book: Chap 8]
    8. Feature Selection xx-xx
    9. Combining Models xx-xx
    10. Unsupervised learning: K-Means, GMM, EM xx-xx
    11. Eigenanalysis: PCA, LDA, Subspaces xx-xx