Course Description

Contents and Outcomes:
Machine learning techniques that allow computers to form representations, make predictions, or apply controls automatically from data have become increasingly prevalent in modern technologies and are opening up new approaches in a wide range of domains. This course provides an introduction to the field of Machine Learning and covers fundamental and state-of-the-art machine learning algorithms. It will cover unsupervised, supervised, semi-supervised, as well as reinforcement learning techniques with a focus on unsupervised and supervised learning. Students completing this course will gain an understanding of the area of machine learning and the ways in which different learning algorithms operate. They will also be able to apply the covered methods to real-world problems.

Many of the techniques covered in this course are based on statistics and linear algebra and knowledge in these areas is required. Prerequisite for this course is Data Modeling (CSE 5301), an advanced (equivalent) statistics course, or consent of instructor. Prior knowledge of Artificial Intelligence (CSE 5361) and Algorithms (CSE 5311) is useful.

Course Materials:
The recommended textbook for this course is:
Pattern Recognition and Machine Learning, Christopher M. Bishop, 2006.
Additional readings in the form of book chapters or research papers will be made available either through the course Canvas site.

Course Format:
This course will be taught as a Synchronous Online course. All lectures, quizzes, and assignments in this course will be online with lectures on Microsoft Teams and quizzes and assignments on Canvas.

Technology Requirements;
Every student will have to have access to a computer and Microsoft Teams as well as Canvas to be able to participate in lectures and for quizzes. Students are expected to have a webcam and should have this camera turned on during lectures to be able to effectively participate in the class, and during quizzes which might use Canvas' Lockdown Browser. In addition, students will have to have access to a computer to perform the programming components of the assignments and projects. For the latter, programming can use any standard programming language but should not depend on any particular programming environment (such as Microsoft Studio) to run. If the instructor or GTA can not compile and/or run code, the student is responsible to provide an appropriate environment to evaluate the code.

E-mail and WWW page:
There is a course web page at as well as a Canvas and a Microsoft Teams page. All changes and supplementary course materials will be made available through Canvas and usually through the web site. In addition, necessary changes or important announcements will also be distributed by through Canvas.

Tentative Office Hours:
Office hours for the course will be held by the instructor as Teams meetings T,Th 5:00pm-6:00pm Central time and W 10:00am-11:00am Central time. Times are subject to change and will be posted.

Teaching Assistants:
There will be a Teaching Assistants for this course. Their details will be announced on Canvas.