University of Kentucky
MA 721: Topics in Numerical Analysis: Deep Learning
MWF 1:00 pm - 1:50 pm, CB 347
Dr. Qiang Ye
Office: 735 Patterson Office Tower
Email: qye3 "at" uky . edu
Office Hours: MWF 2:00-3:00 pm
Deep Learning by
Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press, 2016
In this course, we study a widely applicable class of machine learning methods called deep learning. The following topics will be covered.
We will begin with an overview of numerical optimization and probability and information theory. Linear algebra is another area of math that will be used substantially. We will not devote time to cover them as most of the class have taken MA/CS 522 or 622 before. Those who have not taken a numerical linear algebra class are encouraged to consult one of reference books listed below. The most pertinent topics include linear least squares problems, singular value decompositions, and iterative methods such as the steepest descent and conjugate gradient algorithms.
- Deep Feedforward Networks.
- Regularization for Deep Learning
- Optimization for Training Deep Models.
- Convolutional Networks
- Sequence Modeling: Recurrent and Recursive Networks
- Unsupervised Learning (Autoencoders and Deep Generative Models)
- Other Topics as time permits
Familiarity with multivariate calculus, linear algebra and numerical analysis will be assumed. Programming in Python will be required.
We will use Python based toolboxs such as Keras/Theano/Tensorflow. You may choose to use any of them. Below are some links for setting up Keras/Theano/Tensorflow on Windows 10.