Skip to main content

Robust and Generalizable Machine Learning through Generative Models,Adversarial Training, and Physics Priors

Abstract Machine learning has demonstrated great potential across a wide range of applications such as computer vision, robotics, speech recognition, drug discovery, material science, and physics simulation. Despite its current success, however, there are still two major challenges for machine learning algorithms: limited robustness and generalizability.

The robustness of a neural network is defined as the stability of the network output under small input perturbations. It has been shown that neural networks are very sensitive to input perturbations, and the prediction from convolutional neural networks can be totally different for input images that are visually indistinguishable to human eyes. Based on such property, hackers can reversely engineer... (more)
Created Date 2019
Contributor Yao, Houpu (Author) / Ren, Yi (Advisor) / Liu, Yongming (Committee member) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Marvi, Hamidreza (Committee member) / Arizona State University (Publisher)
Subject Engineering
Type Doctoral Dissertation
Extent 141 pages
Language English
Note Doctoral Dissertation Aerospace Engineering 2019
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Full Text
8.3 MB application/pdf
Download Count: 234

Description Dissertation/Thesis