Data Science (DATS)

Explanation of Course Numbers

  • Courses in the 1000s are primarily introductory undergraduate courses
  • Those in the 2000s to 4000s are upper-division undergraduate courses that can also be taken for graduate credit with permission and additional work
  • Those in the 6000s and 8000s are for master’s, doctoral, and professional-level students
  • The 6000s are open to advanced undergraduate students with approval of the instructor and the dean or advising office

DATS 6101. Introduction to Data Science. 3 Credits.

Basic techniques of data science; algorithms for data mining; and basics of statistical modeling. Concepts, abstractions, and practical techniques. Prerequisites: STAT 2118 or permission of the instructor. Recommended background: An undergraduate degree with a strong background in science, mathematics, or statistics. (Same as STAT 6289).

DATS 6102. Data Warehousing. 3 Credits.

Fundamentals and practical applications of data warehousing, including planning requirements, infrastructure, design, and maintenance. Prerequisites: STAT 2118 or permission of the instructor. Recommended background: An undergraduate degree with a strong background in science, mathematics, or statistics.

DATS 6103. Introduction to Data Mining. 3 Credits.

Concepts, principles, and techniques related to data mining; strengths and limitations of various data mining techniques, including classification, association analysis, and cluster analysis. Restricted to candidates for the MS or graduate certificate in data science; permission of the instructor may be substituted. Prerequisites: DATS 6101 or permission of the instructor.

DATS 6201. Numerical Linear Algebra and Optimization. 3 Credits.

Linear and quadratic programming, nonlinear equations, global and unconstrained optimization, and general linearly and nonlinearly constrained optimization as used in data science. Restricted to students in the MS in data science program or with the permission of the instructor. Prerequisites: MATH 2184 or MATH 2185. Recommended background: An undergraduate degree with a strong foundation in science, mathematics, or statistics.

DATS 6202. Machine Learning I: Algorithm Analysis. 3 Credits.

This course is a practical approach to fundamentals of algorithm design associated with machine learning. Topics include techniques of statistical and probability theory, combinatorial optimization, and factor graph and graph ensemble as used in machine learning. Restricted to Designed primarily for students in the Data Science program, however other students with appropriate backgrounds can register for the course with permission of the instructor. Recommended background: An undergraduate degree with a strong background in science, mathematics, or statistics. (Same as PHYS 6620).

DATS 6203. Machine Learning II: Data Analysis. 3 Credits.

This course is a practical approach to fundamentals of machine learning with an emphasis on data analysis; i.e., how to extract useful information from different datasets Topics include linear models, error and noise, training and testing methods, and generalization as used in machine learning. Restricted to Designed primarily for students in the Data Science program, however other students with appropriate backgrounds can register for the course with permission of the instructor. Prerequisite: DATS 6101. Recommended background: An undergraduate degree with a strong background in science, mathematics, or statistics.

DATS 6401. Visualization of Complex Data. 3 Credits.

This course is a practical approach to fundamentals of data visualization specifically for data science professional. It covers all significant topics, including graphics, discrete and continuous variables, clustering and classification. Restricted to candidates for the MS or graduate certificate in data science; permission of the instructor may be substituted. Prerequisites: DATS 6101, DATS 6102, and DATS 6103.

DATS 6402. High Performance Computing and Parallel Computing. 3 Credits.

Practical approach to high performance computing specifically for the data science professional. Topics such as parallel architectures and software systems, and parallel programming. Restricted to students in the MS or graduate certificate in data science programs or with permission of the instructor. Prerequisites: DATS 6101, DATS 6102 and DATS 6103.

DATS 6450. Topics in Data Science. 3 Credits.

Topics vary by semester. May be repeated for credit provided topic differs. See department for more details. Restricted to students in the master’s and graduate certificate in data science programs. Restricted to students in the master's and graduate certificate programs in data science. Prerequisites: DATS 6101 or permission of the instructor.

DATS 6499. Data Science Applied Research. 3 Credits.

Students conduct research projects under the supervision of the instructor. Project topics build on the knowledge and skills acquired during the data science program. Permission of the instructor required prior to enrollment.

DATS 6501. Data Science Capstone. 3 Credits.

Practical application of the knowledge and skills acquired during the master’s program. Capstone team projects are chosen in consultation with the instructor. In addition to the specific prerequisite courses, completion of five pre-approved data science courses is required prior to enrollment. Restricted to students in their final semester of the MS in data science program. Prerequisites: DATS 6101, DATS 6102 and DATS 6103.

DATS 6810. Hot Topics in Big Data Analytics. 3 Credits.

This course will enhance students’ big-data analysis and statistical skills, and is aimed at upper-level undergraduate and graduate students from the physical, biological and social sciences. In addition to overviewing standard tools using R, it will expose students to current thinking about real data, analysis and modeling in our ‘non-normal’ world where distributions are fat-tailed rather than approximately normal, and where processes are bursty rather than approximately Poisson. Its cross-disciplinary approach will also help address the likely challenge facing next-generation researchers and employees, to ‘understand’ real-world data not only through statistical tests, but also by building generative simulations (e.g. in C) that reproduce the statistical stylized facts of real-world data sets. Other topics to be discussed include networks, machine-learning, as well as web-scraping of data — e.g. from social media sources. Restricted to Graduate and advance undergraduate students with permission of the instructor. Prerequisite: MATH 2184. Recommended background: Competency in single-variable calculus; MATH 2233 would be beneficial but is not strictly necessary. (Same as PHYS 6810).