*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Two sides of one tapestry: Joint Source-Channel Coding and Deep Generative Models
Committee:
Dr. Fekri, Advisor
Dr. Bloch, Chair
Dr. AlRegib
Abstract:
The objective of the proposed research is to study the intersection between Joint Source-Channel Coding and Deep Generative Models. For Joint Source-Channel Coding we explore how deep learning techniques can be used to design encoders and decoders for problems where human intuition has failed to give us good performing solutions. We also show that Joint Source-Channel Coding problem can be posed as a Variational Autoencoder learning problem thus allowing us to make use of the vast literature in machine learning. On the other side, we will also explore how the insight gained from Joint Source-Channel Coding can benefit the field of Deep Generative Models specifically in terms of improving their training algorithms.
