Schedule of Classes

Machine learning and intelligent systems. Covers the major approaches to ML and IS building, including the logical (logic programming and fuzzy logic, covering ML algorithms), the biological (neural networks and deep learning, genetic algorithms), and the statistical (regression, Bayesian and belief networks, Markov models, decision trees and clustering) approaches. Students use ML to discover the knowledge base and then build complete, integrated, hybrid intelligent systems for solving problems in a variety of applications. Cross listed with CS 462. For cross-listed undergraduate/graduate courses, the graduate-level course will have additional academic requirements beyond those of the undergraduate course.

Covers topics including basic concepts and principles of software requirements engineering, the requirements engineering process, requirements elicitation, requirements analysis, requirements specification, system modeling, requirements validation and requirements management, and techniques, methods, and tools for requirements engineering and software systems requirements modeling (including structured, object-oriented and formal approaches to requirements modeling and analysis).

Individual study in an area of computer science relevant to the student's professional goals and not covered in a formal course offered by the department. May be repeated twice for a maximum of 6 credit hours.