event
Ph.D. Proposal Oral Exam - Yashas Saidutta
Primary tabs
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.
Status
- Workflow Status:Published
- Created By:Daniela Staiculescu
- Created:10/02/2019
- Modified By:Daniela Staiculescu
- Modified:10/02/2019
Categories
Keywords
Target Audience