University of Kentucky
MA 721: Selected Topics in Numerical Analysis: Deep
Learning Algorithms
Fall 2025
MWF 1:00 pm - 1:50 pm, Chemistry-Physics Bldg Rm.183
Instructor
Dr. Qiang Ye
Office: 735 Patterson Office Tower
Phone:257-4653
Email: qye3 "at" uky . edu
Office Hours: MWF 3:00-4:00
pm
Textbook
There will be no required text, but the following book will be a good source of references:
- Dive into Deep Learning by by Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J.
Smola, Cambridge University Press, 2023.
Course Announcement
Here is a course announcement where most information can be found.
Syllabus
In this course, we study a widely applicable class of machine learning methods called deep learning. We will cover the following topics:
- Introduction to Machine Learning and Linear Models.
- Fully Connected Neural Networks
- Optimization and Regularization
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs), Transformer, and Language Models
- Graph Convolutional Networks (GCNs)
- Generative Models for Unsupervised Learning
- Principal Component Analysis (PCA)
- Autoencoder, and Variational Autoencoder (VAE)
- Generative Adversarial Networks (GANs)
- Stochastic Differential Equations and Diffusion Models
Selected materials from optimization,
linear algebra, and probability/information theory will be
reviewed.
Prerequisites
Familiarity with multivariate calculus, linear algebra, numerical methods, and programming in Python.