40717 Machine Learning

Course Description

In this course, we will introduce the field of machine learning, focusing on the core concepts of supervised, unsupervised, and reinforcement learning. In supervised learning, we learn a function mapping between the input and the output based on input data labeled with the desired output. The purpose of unsupervised learning is to discover latent structures in input samples when output labels are not available. We will discuss reinforcement learning models and algorithms when evaluative feedback is available.

Course Information

• Instructor: Hamid Beigy

• Teaching Assistants: Fariba Lotfi

• Time and Location: Saturday/Monday: 9:00 am - 10:30 am, CE 103 virtual class

• Contact: Please contact the teaching staffs on Piazza site.

Required Texts

1. [BSH] Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag, 2006.

2. [MIT] Tom M. Mitchell, Machine Learning, McGraw-Hill, 1997.

3. [MUR12] Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, The MIT Press, 2012.

4. [MUR22] Kevin P. Murphy, Probabilistic Machine Learning: An Introduction, The MIT Press, 2022.

5. [SB] Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second edition. The MIT Press, 2018.

6. [HAL] Hal Daume III, A Course in Machine Learning, 2014.

Grading Policy

1. 25%: Mid-term exam 1 (1402/01/30).

2. 25%: Final exam

3. 30%: Homeworks.

4. 10%: Quiz.

5. 10%: Paper & Explore a theoretical or empirical question and present it. Deadline for choosing paper: 1402/01/30.

Lecture Schedule