Table of Content

1. Basic Information
2. Highlights
3. Course Description
4. Assignments
5. Additional Course Information

1. Basic Information

• Instructor: Yangfeng Ji (Office hour: Friday 9 AM, Rice 510 and Zoom)
• Semester: Spring 2023
• Location: Rice 130
• Time: Tuesday and Thursday 11:00 AM – 12:15 PM
• TA:
  • Oishee Hoque (Office hour: Wednesday 11 AM, at Zoom)
  • Aparna Kishore (Office hour: Thursday 4 PM, at Rice 542)
  • Nusrat Mozumder Office hour: (Tuesday 1 PM, on Zoom)
  • Sanchit Sinha (Office hour: Monday 2 PM, at Rice 442)
  • Dane Williamson (Office hour: Friday 1 PM, on Zoom)

2. Highlights

• Course schedule
• Homework submission template
• Instructions for final project

3. Course Description

• The goal of this course is to understand basic concepts and algorithms in machine learning.
• Teaching how to use machine learning packages (e.g., sklearn) will not be a focus of this course. Although, we do have demos built upon these packages for explaining the concepts and algorithms.
• Deep learning (or neural network modeling) will only be a small part of this course.

3.1 Topics

Most of the course materials (and assignments) are adopted from Shalev-Shwartz and Ben-David’s textbook on machine learning. Particularly, the topics overed in this course are:

• Introduction to learning theory
• Linear classification and regression
• Support vector machines and kernel methods
• Model selection and validation
• Neural networks and deep learning
• Optimization
• Generative modeling

For more information about this course, please checkout the [schedule](schedule.

3.2 Prerequisites

In addition to the programming skill, basic probability theory and linear algebra are highly recommended.

• Programming and Algorithm: CS 2150 or CS 3100 with a grade of C- or better
  • We will use Python for our homework assignments
• Probability: APMA 3100, APMA 3110, MATH 3100, or equivalent
  • Example topics: definition of probability, basic probability distributions (e.g., Gaussian, Bernoulli, and Multi-nominal)
• Linear Algebra: Math 3350 or APMA 3080 or equivalent
  • Example topics: matrix-vector multiplication, special metrices, linear transformation, matrix factorization (e.g., SVD)

3.3 Textbook

• [UML] Shalev-Shwartz and Ben-David. Understanding Machine Learning: From Theory to Algorithms. 2014
• [DL] Goodfellow, Bengio, and Courville. Deep Learning. 2016

Additional

• [PRML] Bishop. Pattern Recognition and Machine Learning. 2006
• [MRT] Mohri, Rostamizadeh, and Talwalkar. Foundations of Machine Learning. 2nd Edition. 2018

4. Assignments

There are three parts of assignment

• Homework (70 points)
  • There are five assignments, each of them will have about two weeks to finish. Students can find the tentative release dates of the homework assignments on the schedule page
  • Each homework is worth 14 points
  • Students should work independently on homework assignments
• Quiz (10 points)
  • There are ten quizzes in total, each of them is worth 1 point
  • The quiz will be distributed during lecture
  • participation is more important than correctness of the answer
• Final project (20 points)
  • There will be several pre-defined projects and students will select one of them for their final project
  • Students need to form groups for their final project, the size of each group should be 3 – 4 students
  • More details about final project will be released soon

4.1 Grading Policy

For more information about grading policy, please visit this page.

5. Additional Course Information

For the information about the honor code and other course policies, please visit this page.