Interdisciplinary AI Courses to Take This Spring at UMD

The University of Maryland offers an unparalleled educational experience in artificial intelligence (AI) through both innovative curriculum and cutting-edge research. This combination positions UMD students to be leaders in the AI landscape. 

From game design to transforming messy data to applying data science to real-world issues, UMD’s Department of Computer Science offers plenty of interdisciplinary AI classes taught by expert faculty members.

Now that it’s time to register for courses for the Spring 2026 semester, check out some unique options from CMNS for undergraduate students to study AI and learn its practical applications.

CMSC320: Introduction to Data Science

CMSC320 teaches students how to transform unstructured, messy data into actionable insights. The Department of Computer Science offers three sections of this course, taught by lecturers Fardina Alam, Anna Evtushenko and Maksym Morawski. The curriculum provides an introduction to the data science pipeline by covering statistical data analysis, basic data mining and machine learning algorithms, large-scale data management, cloud computing and information visualization.

CMSC421: Introduction to Artificial Intelligence

Taught by Computer Science Professor William Regli and Lecturer Sujeong Kim, this course introduces students to a range of AI concepts and methods. Topics include automated heuristic search, planning, games, knowledge representation, logical and statistical inference, natural language processing, computer vision, robotics, cognitive modeling and intelligent agents. Students obtain a hands-on feel for these topics by completing their own programming projects.

CMSC422: Introduction to Machine Learning

Machine learning has advanced significantly over the past 70 years. Taught by Computer Science Senior Lecturer Mohammad Nayeem Teli, this course provides a broad overview of existing methods for machine learning and an introduction to adaptive systems in general. The curriculum emphasizes the practical aspects of machine learning and data mining.

CMSC425: Game Programming

Students learn about game hardware and systems, the principles of game design, object and terrain modeling, game physics, artificial intelligence for games, aural rendering and more in this course taught by Computer Science Lecturer Stevens Miller. These topics are reinforced through the design and implementation of a working computer game.

CMSC426: Computer Vision

Computer vision allows computers to analyze and interpret images and videos. CMSC426, taught by Computer Science Associate Professor Jia-Bin Huang, introduces students to basic computer vision concepts and techniques. This includes image filtering and edge detection, 3D reconstruction of scenes using stereo and structure from motion, and object detection, recognition and classification.

CMSC454: Algorithms for Data Science

In CMSC454, students learn how to process high volumes of data. The fundamental methods in this curriculum include stream processing, locally sensitive hashing, web search methods, page rank computation, dynamic graph algorithms and more. The course is taught by Distinguished University Professor of Computer Science Aravind Srinivasan.

CMSC470: Introduction to Natural Language Processing

Taught by Computer Science Assistant Professors Rachel Rudinger and Sarah Wiegreffe, CMSC470 introduces students to fundamental techniques for automatically processing and generating natural language with computers. Students apply machine learning techniques in a series of assignments designed to address a core application, such as question answering or machine translation.

—Story adapted from a release by CMNS