ORIE 4742

Information Theory, Probabilistic Modeling, & Deep Learning with Scientific & Financial Applications

Course Description

Course information provided by the 2016-2017 Catalog.

This course is about building and understanding machine learning models for scientific and financial applications.  It will cover foundational aspects of information theory and probabilistic inference as they relate to model construction and deep learning.  Topics include hamming codes, repetition codes, entropy, mutual information, Shannon information, channel capacity, likelihood functions, Bayesian inference, graphical models, and deep neural networks. The section on deep neural networks will consider fully connected, convolutional, recurrent, and LSTM networks, generative adversarial training, and variational autoencoders.

Prerequisites/Corequisites Prerequisites: ORIE 3500 and MATH 2940 or equivalent. Programming experience at the level of CS 2110 or equivalent. Exposure to statistical machine learning at the level of ORIE 4740, ORIE 4741 or equivalent or permission of the instructor.

When Offered Spring.

View Enrollment Information