Washington University in St. Louis
Department of Computer Science and Engineering


CSE 417T: Introduction to Machine Learning

Fall 2022

ANNOUNCEMENTS

OVERVIEW

This course is an introduction to machine learning, focusing on supervised learning. We will cover the mathematical foundations of learning as well as a number of important techniques for classification and regression, including linear and logistic regression, neural networks, nearest neighbor techniques, kernel methods, decision trees, and ensemble methods. Note that the material in this course is a prerequisite for CSE 517A, the graduate level machine learning class. The overlap with CSE 511A (Artificial Intelligence) is minimal.

STAFF

Instructors:
Instructor Email Lecture Time Classroom
Chien-Ju Ho chienju.ho at wustl dot edu Tue/Thu 2:30PM-3:50PM Hillman / 70

TAs:
There are several graduate and undergraduate TAs for the class. All assistants will hold regular office hours, answer questions on Piazza, and grade homeworks. The list of TAs and their office hours will be announced on Piazza.

POLICIES

Detailed policies are in the official syllabus below. A few points to highlight: please read and understand the collaboration policy and the late day policy. There will be two exams, each covering approximately half the course material, and no separate final exam.

TEXTBOOKS

The main course textbook is: We also plan to cover some sections of the following book:

PREREQUISITES

CSE 247, ESE 326 (or Math 3200), Math 233, and Math 309 (can be taken concurrently) or equivalents. If you do not have a solid background in calculus, probability, and computer science through a class in data structures and algorithms then you may have a hard time in this class. Matrix algebra will be used and is fundamental to modern machine learning, but it's OK to take that class concurrently.

SCHEDULE, READING, AND ASSIGNMENTS

Date Topics Readings Assignments
August 30 Introduction. Course policies. Course overview. Perceptron learning algorithm. LFD 1.1, 1.2. Slides hw0
Submission Instructions
September 1 Generalizing outside the training set, Hoeffding's inequality. LFD 1.3. Slides
September 6 Multiple hypotheses. LFD 1.3. Slides
September 8 Error and noise. Infinite hypothesis spaces, growth functions. LFD 1.4; 2.1.1. Slides hw1 (Due: Sep 23)
September 13 VC generalization bound, VC Dimension. LFD 2.1-2.2. Slides
September 15 Bias-variance tradeoff. LFD 2.3. Slides
September 20 Linear classification, linear regression. LFD 3.1-3.2. Slides
September 22 Logistic regression, gradient descent. LFD 3.3. Slides hw2 (Due: Oct 7)
September 27 Nonlinear transformation. Overfitting. LFD 3.4 and 4.1. Slides
September 29 Regularization. LFD 4.2. Slides