University of Kentucky
MA 721: Topics in Numerical Analysis: Deep Learning
MWF 1:00 pm - 1:50 pm, CB 343
Dr. Qiang Ye
Office: 735 Patterson Office Tower
Email: qye3 "at" uky . edu
Office Hours: MWF 2:00-3:00 pm
There will be no required text, but the following books will be good sources of references:
In this course, we study a widely applicable class of machine learning methods called deep learning. We will cover the following topics:
Selected materials from optimization, linear algebra, and probability theory/information theory will be covered.
- Deep Feedforward Neural Networks.
- Convolutional Neural Networks
- Recurrent Neural Networks
- Deep Generative Models for Unsupervised Learning
Familiarity with multivariate calculus, linear algebra and numerical methods will be assumed. Programming in Python will be required.
The course grade will be based on programming projects (60%) and an in-class presentation (40%).
Some references and links
Below are some links and books on numerical linear algebra, optimization, and machine learning that may be helpful.