MATH 076 (01)

[Topics in Applied Mathematics]

Mathematics of AI and Large Language Models

This course is a mathematical introduction to artificial intelligence and large language models. We will study vectors, matrices, tensors, embeddings, gradient descent, automatic differentiation, attention mechanisms, and generative models. The course will emphasize hands-on mathematical examples, especially simple low-dimensional versions of ideas that appear in modern AI systems.

Course Information

Term: Summer 2026 (June 25, 2026 - August 26, 2026)

Class meetings: Monday, Wednesday, Friday, 2:10–3:15 PM

X-hour: Thursday, 1:20–2:10 PM

Course Grade

Component Points
Homework 10
Class Activities 10
Quiz 20
Final Project 20
Midterm 30
Final Exam 10
Total 100
Notes:

1) Homework and class activities are graded for completion (you don't need to get a complete correct answer to get the points), with no feedback.

1) Quiz problems are selected from homework problems of that week, with possibly a minor modification.

Weekly Plan

Week 1: Overview and Foundations (June 25 – July 1)

Overview of AI, neural networks, LLMs, tensors, training, and generative models. Review of vectors, matrices, and functions.

Week 2: From Linear Algebra to Linear Layers (July 2 – July 8)

Vectors, matrices, matrix multiplication, linear classifiers, and neural network layers.

Week 3: From Vector Geometry to Embeddings (July 9 – July 15)

Norms, distances, dot products, cosine similarity, projections, high-dimensional geometry, word embeddings, matrix factorization, and encoder-decoder models.

Week 4: From Tensor Product Spaces to Tensor Computation (July 16 – July 22)

Tensors, tensor products, tensor networks, contractions, batching, and tensor shapes.

Week 5: From Multivariate Calculus to Gradient Descent (July 23 – July 29)

Partial derivatives, gradients, chain rule, loss functions, gradient descent, and training.

Week 6: From Dual Numbers to Automatic Differentiation (July 30 – August 5)

Dual numbers, computational graphs, automatic differentiation, and backpropagation.

Midterm: The midterm will take place during this part of the course.

Week 7: From Dynamics to LLMs I (August 6 – August 12)

Vector fields on a high-dimensional sphere. Vector fields represented by kernels.

Week 8: From Dynamics to LLMs II (August 13 – August 19)

Many-particle dynamics on the sphere, next-token prediction, and the attention mechanism.

Week 9: Project Presentations / From Probability to Generative Models (August 20 – August 26)

Project presentations. Time permitting: probability distributions, conditional probability, maximum likelihood, diffusion models, and final project discussions.

Course Goals

By the end of the course, students should be able to:

Accessibility Needs

Students with disabilities who may need disability-related academic adjustments and services for this course are encouraged to see me privately as early in the term as possible. Students requiring disability-related academic adjustments and services must consult the Student Accessibility Services office (Carson Hall, Suite 125, 646-9900). Once SAS has authorized services, students must show the originally signed SAS Services and Consent Form and/or a letter on SAS letterhead to me. As a first step, if students have questions about whether they qualify to receive academic adjustments and services, they should contact the SAS office. All inquiries and discussions will remain confidential.