Scribd
Upload
12 views6 pages

AI and ML Course Syllabus Overview

The document outlines a course on Artificial Intelligence and Machine Learning taught by Dr. Yunwen Lei at The University of Hong Kong, scheduled for Wednesdays from 6:30pm to 9:20pm. It includes details on assessments, course content covering statistical learning theory, algorithmic stability, and optimization, as well as prerequisites and course materials. The course aims to provide a comprehensive understanding of statistical learning theory and problem-solving at the intersection of machine learning and optimization.

Uploaded by

9gt5rqjjnq
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views6 pages

AI and ML Course Syllabus Overview

The document outlines a course on Artificial Intelligence and Machine Learning taught by Dr. Yunwen Lei at The University of Hong Kong, scheduled for Wednesdays from 6:30pm to 9:20pm. It includes details on assessments, course content covering statistical learning theory, algorithmic stability, and optimization, as well as prerequisites and course materials. The course aims to provide a comprehensive understanding of statistical learning theory and problem-solving at the intersection of machine learning and optimization.

Uploaded by

9gt5rqjjnq
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Topics in Artificial Intelligence and Machine Learning

Introduction

Yunwen Lei

Department of Mathematics, The University of Hong Kong

January 17, 2025


Course Information
Course Syllabus

Time: Wednesday 6:30pm-9:20pm (2 breaks)

Assessment: 3 homework assignments and 1 class test (50%), and final exam
(50%)
▶ 1st assignment: Concentration inequality and complexity analysis
▶ 2nd assignment: Convex analysis and algorithmic stability
▶ 3rd assignment: learning theory, Multiclass learning, min-max optimization
▶ We will give you two weeks to finish each assignment

Class test: March 19, 2 hour exam in class (tentative)

Moodle will be used for course communication, announcements, homework


assignments, etc.
Course Syllabus: Content (tentative)
Statistical Learning Theory (3 or 4 weeks)
▶ Optimization and generalization
▶ Concentration inequality
▶ Complexity measures
Algorithmic Stability (3 or 4 weeks)
▶ Convex analysis
▶ Algorithmic stability
▶ Regularization schemes
▶ Stochastic gradient descent
Multi-class learning and optimization (1 week)
Min-max optimization (1 week)
Online gradient descent (1 week)

Goal of this course


Demonstrate in-depth and comprehensive understanding of statistical learning
theory
Gain training for solving new problems at the interface of machine learning and
optimization
Course Syllabus

Instructor: Dr. Yunwen Lei


▶ Office: Room 319, Run Run Shaw Building
▶ Email: leiyw@[Link]
▶ Consultation hours:
Tuesday 4:00 pm - 5:30 pm
Thursday 3:00 pm - 4:30 pm
Tutor: Mr. Yufeng Xie
▶ Office: Room 217, Run Run Shaw Building
▶ Email: [Link]@[Link]
Prerequisites: calculus, linear algebra, probability theory (basic).
Course materials: lecture slides and lecture notes
Course Syllabus

Medium level
1 Shalev-Shwartz, Shai, and Shai Ben-David. Understanding machine learning: From
theory algorithms. Cambridge university press, 2014.

2 Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. Foundations of


Machine Learning. MIT Press, Second Edition, 2018.
Advanced level
1 Bach, Francis. [Link] theory from first principles. MIT press,

You might also like