Thesis.pdf (3.86 MB)
Download file

Deep Sequence Models: Learning to Generate Data and Adversarial Attacks

Download (3.86 MB)
thesis
posted on 05.07.2021, 05:55 authored by MAHMOUD AHMED HOSSAMELDEEN MOHAMMAD AHMED IBRAHIM
Understanding sequential data like natural language sentences and learning to model it with generative models are fundamental research problems in artificial intelligence. Solving them helps to create machines that are imaginative and which can perform human-like reasoning and robust decision making. Advanced sequence models will have a significant impact on key areas including drug discovery, autonomous vehicles, and robotics. This thesis advances research in sequence models in two ways: by introducing controlling mechanisms into generative models, and by learning to efficiently generate attacks on natural language models.

History

Campus location

Australia

Principal supervisor

Dinh Phung

Additional supervisor 1

Trung Le

Additional supervisor 2

Viet Huynh

Additional supervisor 3

He Zhao

Year of Award

2021

Department, School or Centre

Clayton School of Information Technology

Course

Doctor of Philosophy

Degree Type

DOCTORATE

Faculty

Faculty of Information Technology