Deep Learning in Unconventional Domains

Author: Cvitkovic, Michael William (Milan0

Year: 2020

Degree: Dissertation (Ph.D.)

Advisor: Vidick, Thomas G.

Committee Members: Yue, Yisong; Wierman, Adam C.; Vidick, Thomas G.; Anandkumar, Anima

Option: Computing and Mathematical Sciences

DOI: 10.7907/v7dm-6r52

Abstract

Machine learning methods have dramatically improved in recent years thanks to advances in deep learning (LeCun et al., 2015), a set of methods for training high-dimensional, highly-parameterized, nonlinear functions. Yet deep learning progress has been concentrated in the domains of computer vision, vision-based reinforcement learning, and natural language processing. This dissertation is an attempt to extend deep learning into domains where it has thus far had little impact or has never been applied. It presents new deep learning algorithms and state-of-the-art results on tasks in the domains of source-code analysis, relational databases, and tabular data.

Files