Artificial Intelligence Theory

Course Description

This course provides a comprehensive introduction to machine learning; the field of computer science concerned with developing programs that automatically improve their performance through experience. Students explore both theoretical foundations and practical applications of algorithms that enable computers to learn from data, including programs that recognize faces, recommend content, and drive autonomous systems. Topics include k-nearest neighbors, statistical learning methods, Bayesian networks, decision tree learning, support vector machines, ensemble methods, unsupervised learning techniques such as clustering and dimensionality reduction, and an introduction to deep learning with neural networks. Through hands-on labs, students implement algorithms using Python and apply them to real-world datasets across domains such as image classification, natural language processing, and predictive analytics. The course emphasizes understanding the assumptions, strengths, and limitations of different approaches, enabling students to select appropriate methods for specific problem contexts. A semester-long research project provides opportunity to engage with current literature and apply machine learning to an original investigation. Letter grade only.

Code

AIML 370

Credits

3

Subject

AIML

Programs That Include This Course

• Bachelor's Bachelor of Science in Artificial Intelligence