Teaching · Fall 2026
CSCI 8945 — Advanced Representation Learning
Advanced Representation Learning examines how machines learn to represent data — classical and deep methods alike — and how those representations power downstream tasks in vision, language, audio, and beyond. Through a research project, students develop and evaluate new representation-learning ideas and write them up as a manuscript. By the end of the course, students will understand the state of the art in representation learning and be able to apply it to real problems.
At a glance
Meets
Tue & Thu, 1:15–2:35 PM (lecture), Miller Plant Sciences 1503
Wed, 1:15–2:10 PM (discussion), Forest Sciences-4 0516
Course info
4 credit hours
Prerequisites: machine learning basics and relevant math (linear algebra, calculus, probability)
Learning outcomes
- Demonstrate understanding of machine learning and deep neural network fundamentals.
- Gain experience deploying deep learning models in computer vision, natural language processing, and audio domains.
Reading materials
No single required textbook — these are useful free references throughout the semester.
- Deep Learning (2016) — Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Free online.
- Dive into Deep Learning (2021) — Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola. Free online.
- Computer Vision: Algorithms and Applications (2022, 2nd ed.) — Richard Szeliski. Free online.
- Machine Learning: A Probabilistic Perspective — Kevin Murphy.
- Foundations of Data Science — Avrim Blum, John Hopcroft, and Ravindran Kannan. Free online.
Evaluation and grading
| Component | Weight |
|---|---|
| Homework (includes individual paper presentation) | 40% |
| Midterm exam (in-class) | 20% |
| Team project & final presentation | 40% |
Team project
Students work in teams of 3–4 on a research project, ideally applying deep learning and representation learning to a real-world problem. Any programming language or software stack is fine. Wednesday sessions throughout the semester are reserved for project and research discussion — use them for feedback and troubleshooting as the project develops. All teams present their final work in a single in-class session on the last day of class, Thu Nov 19.
Individual paper presentations
Starting mid-October, each class period in the "Advanced topics" unit is themed around a research area (e.g., self-supervised learning, generative models, reasoning). Students individually choose and present one research paper related to that day's theme, leading discussion with the class. With roughly 22 students across 10 themed sessions, expect about 2 presenters per session.
Class schedule
Regular lectures run Aug 18 – Nov 17; final project presentations are Thu Nov 19, the last day of class for this meeting pattern. All dates verified against the UGA academic calendar.
| Date | Day | Type | Topic |
|---|---|---|---|
| Introduction | |||
| Aug 18 | Tue | Lecture | Introduction and overview |
| Aug 19 | Wed | Lecture | Course topics |
| Aug 20 | Thu | Lecture | Data and dimensionality |
| Aug 25 | Tue | Lecture | Dimension reduction, metric learning, PCA, MDS |
| Aug 26 | Wed | Discussion | How to do research? |
| Aug 27 | Thu | Lecture | Structures in data spaces, manifolds, subspaces, sparse coding |
| Vision | |||
| Sep 1 | Tue | Lecture | Pixels, 3D points, and cameras |
| Sep 2 | Wed | Discussion | How to read a paper? |
| Sep 3 | Thu | Lecture | Image operations and image semantics |
| Sep 8 | Tue | Lecture | Videos |
| Sep 9 | Wed | Discussion | How to write a paper? / project proposal guidance |
| Sep 10 | Thu | Lecture | Image subspaces and manipulations |
| Language | |||
| Sep 15 | Tue | Lecture | Representing words and sentences |
| Sep 16 | Wed | Discussion | Project and research discussion |
| Sep 17 | Thu | Lecture | Language model pretraining |
| Sep 22 | Tue | Lecture | NLP tasks |
| Sep 23 | Wed | Discussion | Project and research discussion |
| Sep 24 | Thu | Lecture | Zero-shot and in-context learning |
| Audio | |||
| Sep 29 | Tue | Lecture | Representing sound |
| Sep 30 | Wed | Discussion | Project and research discussion |
| Oct 1 | Thu | Lecture | Audio generation and editing |
| Multi-modal | |||
| Oct 6 | Tue | Lecture | Overview of multi-modal learning |
| Oct 7 | Wed | Discussion | Project and research discussion |
| Oct 8 | Thu | Lecture | Multimodal representation alignment |
| Advanced topics — student paper presentations | |||
| Oct 13 | Tue | Midterm | In-class midterm exam |
| Oct 14 | Wed | Discussion | Project and research discussion |
| Oct 15 | Thu | Presentations | Unsupervised learning |
| Oct 20 | Tue | Presentations | Self-supervised learning |
| Oct 21 | Wed | Discussion | Project and research discussion |
| Oct 22 | Thu | Presentations | Domain adaptation and transfer learning |
| Oct 27 | Tue | Presentations | LLM finetuning |
| Oct 28 | Wed | Discussion | Project and research discussion |
| Oct 29 | Thu | Presentations | Generative models |
| Nov 3 | Tue | Presentations | AI agents |
| Nov 4 | Wed | Discussion | Project and research discussion |
| Nov 5 | Thu | Presentations | Time series |
| Nov 10 | Tue | Presentations | Understanding LLM, VLM, etc. |
| Nov 11 | Wed | Discussion | Project and research discussion |
| Nov 12 | Thu | Presentations | Graphs / graph representation learning |
| Nov 17 | Tue | Presentations | Reasoning |
| Nov 18 | Wed | Discussion | Project and research discussion / final presentation prep |
| Project | |||
| Nov 19 | Thu | Presentations | Final project presentations (in class, 1:15–2:35 PM) |
| Nov 23–27 | — | Thanksgiving break, no class | |
| Dec 2 | Wed | Reading day | |
| Dec 3–9 | — | Final exam period (no additional meeting for this course) | |
Thu Nov 19 is this course's last class meeting. Dec 1's university-wide makeup schedule applies only to WF/Friday-only meeting patterns, not Tue/Wed/Thu.