Deep Learning and Large Language Models: An Introduction
QAC 388
Spring 2026
| Section:
01
|
You have probably used ChatGPT, DeepSeek, Midjourney, or another generative AI in your lifetime. But how do these tools actually work? This course will help you answer that question by introducing you to the theory and practice of deep learning, the fundamental technology underlying generative AI. Students will learn the building blocks of modern neural networks, including matrix and vector operations, embeddings, backpropagation, and attention. This will culminate in the implementation of the original GPT transformer language model from scratch in PyTorch. We will then explore extensions of transformers in other modalities, including vision and diffusion transformers for understanding and generating images, and transformers for time series analysis. Along the way, we will cover other types of neural networks, including multilayer perceptrons, CNNs, and RNNs. We will use these models in a variety of practical applications using real-world datasets. |
|
| Credit: 1 |
Gen Ed Area Dept:
None |
| Course Format: Lecture / Discussion | Grading Mode: Graded |
| Level: UGRD |
Prerequisites: (MATH 221 OR MATH 223 OR QAC 220) AND (COMP341 OR QAC 239 OR QAC 305 OR QAC 385 OR QAC 386) |
|
Fulfills a Requirement for: (Applied Data Science Certificate)(Data Analysis Minor) |
|
Past Enrollment Probability: 90% or above |
| SECTION 01 |
Major Readings: Wesleyan RJ Julia Bookstore
Sebastian Rashka. 2024. Build a Large Language Model From Scratch, 8th edition. Manning.
Daniel Jurafsky and James H. Martin. 2025. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition.
Stuart Russell and Peter Norvig. 2021. Artificial Intelligence: A Modern Approach, 4th edition. Pearson
|
Examinations and Assignments:
This is a hands-on course where students will be expected to complete a final project in small teams using the skills they have learned. There will be multiple homework assignments throughout the semester designed as small projects, where students will have to complete a piece of code or perform a larger analysis using a dataset and deep learning model of the instructor¿s choosing. There will be no graded exams, but there will be ungraded quizzes to help check understanding of theoretical concepts. |
Additional Requirements and/or Comments:
An introductory statistics/data analysis background, especially an introductory machine learning background, is a requirement for this course, and that is why several QAC and MATH or COMP courses are listed as qualifying prerequisites. The course includes a strong lab component and programming in Python is a significant part of the course work. At a minimum, students should have prior programming experience, ideally in Python. This experience can arise from prior coursework, research experience, or industry internships. Some background in linear algebra and matrix operations, whether it be theoretical or applied is expected. Pre-req overrides will be approved by the Professor for students who satisfy these basic requirements through other course work.
|
| Instructor(s): Laverghetta,Antonio Times: .M.W... 10:50AM-12:10PM; Location: ALLB204; |
| Total Enrollment Limit: 18 | | SR major: 0 | JR major: 0 | | |
| Seats Available: 0 | GRAD: X | SR non-major: 8 | JR non-major: 7 | SO: 3 | FR: X |
| Drop/Add Enrollment Requests | | | | | |
| Total Submitted Requests: 4 | 1st Ranked: 4 | 2nd Ranked: 0 | 3rd Ranked: 0 | 4th Ranked: 0 | Unranked: 0 |
|
|