MAT2240 Applied Mathematics for AI

Description: This course is a foundational course designed to provide students with the mathematical knowledge and skills essential for understanding artificial intelligence (AI) techniques. The course covers a range of topics from linear algebra, calculus, probability, and statistics, which are crucial for analyzing and solving complex problems in AI. Students will learn how to apply these mathematical tools to build AI algorithms, optimize processes, and make data-driven decisions. The course will also introduce students to numerical methods and computational techniques that are commonly used in AI research and applications. Through a combination of lectures, problem-solving tutorials, and hands-on computational exercises, students will develop a strong mathematical foundation necessary for advanced studies and careers in AI.

Prerequisites: MAT1001 Calculus I, MAT1002 Calculus II, MAT2040 Linear Algebra
Co-requisites: Basic knowledge in MAT3280 Probability Theory, and basic programming skills (Python will be used in this course) Grading policy: Homework (30%), Mid-term exam (35%), Project report (25%), Project presentation (10%)

Reading:

1. Mathematics for Machine Learning, Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
2. An Introduction to Statistical Learning - With Applications in Python, Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, and Jonathan Taylor
3. Probabilistic Machine Learning - An Introduction, Kevin Patrick Murphy
4. Foundations of Machine Learning, Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar