|
|
|
|
|
|
|
|
|
|
Course Criteria
Add courses to your favorites to save, share, and find your best transfer school.
-
3.00 Credits
This course takes a principled and hands-on approach to deep learning with neural networks, covering machine learning basics, backpropagation, stochastic gradient descent, regularization, and universality. Feedforward, convolutional, generative adversarial, and recurrent networks are discussed, as well as autoencoders, other modern architectures, and training techniques. Additional coursework is required for those enrolled in the graduate-level course Prerequisite(s): MATH 1220; MATH 2270 or instructor permission; STAT 3000 or MATH 5710 Prerequisite Recommendation(s): MATH 2210 and MATH 5710 are recommended. Programming experience, preferably in Python, is also strongly recommended Repeatable for credit: N Grade Mode: Standard
-
3.00 Credits
This course introduces topics in computing education research, including learning science, cognitive science, motivation and affect, statistical methods, qualitative methods, pedagogy, assessment, equity and diversity, programming paradigms, and computing for other disciplines. Additional coursework is required for those enrolled in the graduate-level course. Dual-listed as: CS 5750 Repeatable for credit: No Grade Mode: Standard
-
3.00 Credits
Covers advanced topics in database systems, including XML, OODBMS, query optimization, query processing, deductive databases, concurrency, theory of relational databases, normalization, and recovery. Prerequisite/Restriction: 3.0 GPA; grade of B- or better in CS 5800 and enrollment in Computer Science master's or PhD program.
-
3.00 Credits
This course offers a hands-on, programmatic introduction to the nature and computation of wavelets for the analysis and synthesis of digital image and audio data. The course emphasizes the practical significance of wavelet algorithms in computer vision and audio analysis and encourages provocative questions, discussions, and creative thinking. CS 6810 and CS 7810 are cross listed, but CS 7810 requires additional work. Prerequisites: Enrollment in one of the following programs, or instructor permission: MCS (Master of Computer Science) MS in Computer Science MS in Data Science PhD in Computer Science Crosslisted as CS 7810
-
3.00 Credits
This course introduces design principles and techniques for visualizing data. Students learn how visual representations support analysis and understanding of complex data and how to design effective and interactive visualizations. This is a TEAMWORK course. Additional coursework is required for those enrolled in the graduate-level course. Cross/Dual listed as: CS 5820 Prerequisite(s)/Restriction(s): Enrollment one of the following programs, or instructor permission: MCS (Master of Computer Science) MS in Computer Science MS in Data Science PhD in Computer Science
-
3.00 Credits
In this project-based course, students from multiple disciplines work in teams to analyze data from real-world projects. Project teams group technical students from CS with domain experts from outside of CS to analyze data using state-of-the-art data science tools and techniques. Additional coursework is required for those enrolled in the graduate-level course. Registration Restriction(s): Enrollment in one of the following programs, or instructor permission: Master of Computer Science - MCS, Computer Science - MS, Data Science - MS, Computer Science - PhD Dual-listed as: CS 5830 Repeatable for credit: No Grade Mode: Standard
-
3.00 Credits
This course introduces data mining techniques (e.g., graph neural networks) to extract meaningful patterns from graph data. The course also explores social network analysis as the study of social ties through the lens of graph theory. Additional coursework is required for those enrolled in the graduate-level course. Registration Restriction(s): Enrollment in one of the following programs, or instructor permission: Computer Science - Master of Computer Science - MCS Computer Science - MS Data Science - MS Computer Science - PhD Dual-listed as: CS 5840 Repeatable for credit: No Grade Mode: Standard
-
3.00 Credits
This course is intended for students interested in gaining hands-on experience applying computational techniques to solve big data analysis problems. The introduced topics help students learn practical tools to perform the necessary steps of a data analysis project pipeline. Additional coursework is required for those enrolled in the graduate-level course. Registration Restriction(s): Admission to one of the following programs, or instructor permission: Master of Computer Science - MCS, Computer Science - MS, Data Science - MS, Computer Science - PhD Dual-listed as: CS 5850 Repeatable for credit: No Grade Mode: Standard
-
1.00 - 4.00 Credits
This course explores current topics in computer science as determined by advances in the field. Prerequisite/Restriction: Enrollment in one of the following programs, or instructor permission: MCS (Master of Computer Science) MS in Computer Science MS in Data Science PhD in Computer Science Repeatable for credit.
-
1.00 Credits
This course covers a series of one-hour seminars on current research topics presented by computer science faculty. Registration Restriction(s): Enrollment in one of the following programs, or instructor permission: Computer Science - MS Data Science - MS Computer Science - PhD Repeatable for credit: No Grade Mode: Standard
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Privacy Statement
|
Cookies Policy |
Terms of Use
|
Institutional Membership Information
|
About AcademyOne
Copyright 2006 - 2025 AcademyOne, Inc.
|
|
|