COSE361: Artificial Intelligence

What is this course about?

This course aims to develop a solid understanding of core concepts in artificial intelligence, including machine learning, search algorithms, Markov decision processes, and probabilistic reasoning, and to cultivate the ability to apply these concepts to real-world problem solving. Students will also learn to analyze the underlying mechanisms of various AI models, select and implement algorithms appropriate to given problem settings, and interpret results with a practical, problem-oriented mindset.

Resources: There is no required textbook for this class. Slides are mostly self-contained (based on Stanford CS221). You can refer to the following books for further understanding: 

• Russell and Norvig, Artificial Intelligence: A Modern Approach 

• Hastie, Tibshirani, and Friedman, The elements of statistical learning

• Sutton and Barto, Reinforcement Learning: An Introduction

Prerequisites: Students are expected to have the following background:

• Familiarity with basic programming (Python 3)

• Familiarity with basic probability theory

• Familiarity with basic linear algebra

Grading

• Attendance: 10% 

  • Up to five absences will have no penalties. Each absence beyond five will result in a 1% deduction. 

• Programming assignments: 10% 

• Midterm exams: 40% 

• Final exams: 40%

Previous offerings

• 2025 Spring: Student review, Midterm, Final exam