ITCS 8150: Artificial Intelligence

University of North Carolina, Charlotte

Introduction to the basic design principles, concepts and algorithms that can be used to design artificially intelligent systems. Topics include:�Agent models, search algorithms; game playing; constraint satisfaction problems; Markov decision processes and reinforcement learning; supervised learning; knowledge representation; logic; Bayesian and decision networks; sampling; advanced topics as time permits. Students will acquire an understanding of: translating real world problems into formalisms amenable for intelligent agent models and AI techniques; core principles and theories of artificial intelligence, basic AI techniques and algorithms, and computational limitations of AI; design systems that act intelligently and/or learn from experience; recent developments and research within the AI field; independent research in the field of AI. Students should have familiarity with high-level, general-purpose programming language such as Python; fundamental concepts from probability theory; and basic data structures and algorithms such as queues, trees, graphs, hash tables, and sorting.

Average GPA: 3.84

Grade distribution records: 114 students across 17 terms.

Grade distribution

Based on 114 student grade records across 17 terms and 4 professors.

Instructors

• Dewan Ahmed 51 students, Average GPA 3.80
• Zbigniew Ras 35 students, Average GPA 3.85
• Jing Xiao 16 students, Average GPA 3.81
• Ali Sever 12 students, Average GPA 4.00