Georgia Tech Machine Learning Curriculum: A Comprehensive Overview

The Georgia Institute of Technology offers a comprehensive machine-learning curriculum designed to equip students with the knowledge and skills necessary to excel in this rapidly evolving field. This curriculum caters to a diverse audience, from undergraduate students seeking an introduction to AI to Ph.D. candidates pursuing cutting-edge research. This article provides an overview of the machine learning curriculum at Georgia Tech, covering its structure, core components, and resources.

Fundamentals of Machine Learning (FunML)

The Fundamentals of Machine Learning (FunML) course serves as a cornerstone of the AI Minor within the College of Engineering at Georgia Tech. This course is designed to guide students with no prior knowledge of machine learning to a point where they can build and interpret deep learning models. The course uses tabular and image data as primary examples to illustrate concepts.

Prerequisites

Students enrolling in FunML are expected to have a basic understanding of:

Linear algebra
Probability
Multivariable calculus

Course Structure and Content

The FunML course combines theoretical knowledge with practical application.

Assignments: Assignments consist of both analytical problem-solving and hands-on coding exercises, resembling mini-projects. Students are expected to have some background in Python, which is the primary programming language used throughout the course. The AI Makerspace is utilized for coding assignments.

Programming Language: Python is used throughout the course.

Acknowledgment: Any use of the materials from the course must acknowledge Prof. Ghassan AlRegib and the original source.

Graduate Machine Learning Series

Georgia Tech offers a graduate-level Machine Learning Series designed for graduate students and working professionals seeking a principled, hands-on mastery of modern machine learning. This series, initially created by Charles Isbell (Chancellor, University of Illinois Urbana-Champaign) and Michael Littman (Associate Provost, Brown University), features Socratic discussions led by Theodore LaGrow (Georgia Tech). The course has been updated with current examples, tooling, and assessments.

Target Audience

The series is designed for individuals who:

Are comfortable with Python, linear algebra, probability, and basic calculus.
Want a principled, hands-on mastery of modern ML.

Course Progression and Content

The course progresses logically through key areas of machine learning:

Read also: Revolutionizing Remote Monitoring

Supervised Learning: Prediction with labeled data.
Unsupervised Learning: Discovering structure in unlabeled data.
Reinforcement Learning: Sequential decision-making under uncertainty.

Artifacts from each unit feed into the next, creating a cohesive learning experience.

Format and Tools

The course utilizes a variety of tools and platforms:

Video lectures: Delivered in Canvas.
Reports: Written in LaTeX on Overleaf.
Code: Stored in private Georgia Tech GitHub repositories.
Communication: Via Canvas announcements and Ed Discussions.
Supplemental recordings: Weekly recordings on advanced topics aligned to the module.

Learning Outcomes

Upon completion of the series, participants will have:

A portfolio of defensible analyses, models, and policies.
The judgment to explain when and why to use them.

Accessing Course Content

A public version of the course content is available online. To access it, users need to log into their Ed Lessons account.

Course Preparedness

Prospective students can review Course Preparedness Questions to determine if they need to take an introductory course before registering for CS 7641: Machine Learning.

Read also: Boosting Algorithms Explained

Ph.D. Program in Machine Learning

The Ph.D. program at Georgia Tech aims to train students to perform original, independent research in machine learning. The curriculum is designed to provide a strong foundation in both theory and application, culminating in the successful defense of a Ph.D. dissertation.

Core Curriculum

Ph.D. students are required to complete coursework in the following areas:

Mathematical Foundations: This course covers the key subjects from applied mathematics needed for a rigorous graduate program in ML. Particular emphasis will be placed on advanced concepts in linear algebra and probabilistic modeling.
Probabilistic and Statistical Methods in Machine Learning: This course serves as an introduction to the foundational problems, algorithms, and modeling techniques in machine learning.
ML Theory and Methods: This course treats roughly the same material using a mix of applied mathematics and computer science, and each has a different balance between the two.
Optimization: Optimization plays a crucial role in both developing new machine learning algorithms and analyzing their performance.

Elective Courses

In addition to the core courses, students must complete five elective courses to gain breadth in ML.

Responsible Conduct of Research (RCR)

All Ph.D. students must complete an RCR requirement, consisting of an online component and in-person training. The online component is completed during the student’s first semester.

Qualifying Examination

Students must pass a qualifying examination.

Doctoral Minor

Students are required to complete a doctoral minor consisting of two courses (6 hours) outside the area of Machine Learning, with a GPA of at least 3.0. No ML core or elective courses may be used to fulfill this requirement. The courses for the minor should form a cohesive program of study outside the area of Machine Learning and must be approved by the student's thesis advisor and ML Academic Advisor.

Technical Requirements and Software

To participate effectively in the machine learning courses, students should ensure they meet the following technical requirements:

Browser: An up-to-date version of Chrome or Firefox is strongly recommended. Internet Explorer 9 and the desktop versions of Internet Explorer 10 and above are also supported.
Connection speed: 2+ Mbps is recommended; the minimum requirement is 0.768 Mbps download speed.
Operating system:
- PC: Windows XP or higher with the latest updates installed.
- Mac: OS X 10.6 or higher with the latest updates installed.
- Linux: Any recent distribution that has the supported browsers installed.

Academic Integrity

All Georgia Tech students are expected to uphold the Georgia Tech Academic Honor Code.

tags: #Georgia #Tech #machine #learning #curriculum