CS 331: Machine Learning

This course will introduce students to various theoretical and algorithmic aspects of machine learning. Prior knowledge of Probability-Statistics, Linear Algebra and calculus will be required. The course also includes a lab component.

Instructor: Dr. Divya Padmanabhan, Dr. Satyanath Bhat                                                                                           TAs: Vipin, Tina, Manvi, Nimra, Sunny

Timings: Mon 11- 12 , Tue 10-11, Thurs 12 -1,  Lab on Mon 2-5 pm Venue: LH1, Mining Building, IIT Goa

Resources

The following references will be directly relevant for the course.

• Pattern Recognition course by Prof PS Sastry, IISc Bangalore. Link to YouTube playlist 

• Learning from Data course by Prof. Yaser S. Abu Mostafa, CalTech. 

• Textbook: Pattern Recognition and Machine Learning by Christopher Bishop

• Textbook: Introduction to Machine Learning by Ethem Alpaydin

• Textbook: Pattern Classification by Richard O. Duda, Peter E. Hart and David G. Stork

Caution: Being a very popular subject there is a lot of content on the web, however not all resources provide accurate information. Hence please don't blindly believe resources that you find online.

Syllabus 

• Bayes Classifier, Estimator properties, Maximum Likelihood Estimation, Bayesian Estimation

• KMeans clustering, Expectation Maximization Algorithm and theoretical foundations

• Linear Models: Perceptron, Logistic Regression, Regression based classifier, linear regression

• Statistical Learning theory: PAC Learning, VC dimension, Bias Variance Tradeoff

• Feed forward Neural networks, Convolutional Neural Networks

Grading

Theory 70% [For theory part the division out of 100 is: assignments (25%), a mid-term exam (30%), a final exam (30%) , class participation (15%)],   Lab 30%

You are encouraged to discuss problem solving ideas for the assignments with your classmates. However the submitted assignment must be written/typed individually based on your own understanding.

Collaboration is strictly NOT permitted for the mid-term and final exams.  Please approach me if you have any questions during the exams. 

Lectures