40717 Machine Learning

Hamid Beigy, Sharif University of Technology, Fall 2021.

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: 8:30 am - 10:30 am, virtual class
Contact: Please contact the teaching staffs on Piazza site.

Required Texts

[BSH] Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag, 2006.
[MIT] Tom M. Mitchell, Machine Learning, McGraw-Hill, 1997.
[MUR12] Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, The MIT Press, 2012.
[MUR22] Kevin P. Murphy, Probabilistic Machine Learning: An Introduction, The MIT Press, 2022.
[SB] Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second edition. The MIT Press, 2018.

Grading Policy

20%: Mid-term exam 1 (1400/04/17).
25%: Final exam (1400/10/29).
35%: Homeworks.
15%: Quiz.
5%: Paper & Explore a theoretical or empirical question and present it. Deadline for choosing paper: 1400/09/17.

Lecture Schedule

Lecture	Date	Topics	Related Readings and Links	Homeworks & Assignments	Quizes
1	1400-08-08	Introduction: what is machine learning? Overview of suppervised learning	Chapter 1 of BSH Chapter 1 of MUR12 Chapter 1 of MUR22
2	1400-08-10	Overview of probability theory	Chapter 2 of BSH Chapter 1 of MUR22
3 4	1400-08-15 1400-08-17	Regression	Chapter 3 of BSH Chapter 11 of MUR22		Quiz 1
5	1400-08-22	Decision trees	Chapter 3 of MIT
6	1400-08-24	Instance-based learning	Chapter 8 of MIT
7	1400-08-29	Hypothesis Evaluation	Chapter 5 of MIT
8 9 10	1400-09-01 1400-09-06 1400-09-08	Probabilistic Generative Classifiers	Sections 1.5, 2.3, 2.5, & 4.2 of BSH Chapter 5 of MUR22		Quiz 2
11 12	1400-09-13 1400-09-15	Probabilistic Discriminiative Classifiers Linear & Nonlinear Classifiers	Sections 4.3.2, 4.1, 7.1 of BSH Chapters 10 & 17 of MUR22		Quiz 3
	1400-09-17	Mid-term exam		At 10-12
13 14	1400-09-20 1400-09-22	Multi-class Classifiers Ensemble Learning	Section 4.1.2 of BSH Section 14.2 of BSH
15	1400-09-27	Computational Learning Theory	Chapter 7 of MIT		Quiz 4
16 17	1400-09-29 1400-10-04	Dimensionality Reduction	Section 12.1 of BSH Chapter 20 of MUR22
18 19 20	1400-10-06 1400-10-11 1400-10-13	Clustering Reinforcement Learning	Chapter 9 of BSH Chapter 20 of MUR22 Chapters 1-6 of SB		Quiz 5
	1400-11-04	Final exam		At 9-12