Natural robustness of machine learning in the open world
Modern machine learning techniques have demonstrated their excellent capabilities in many areas. Despite the human-surpassing performance in experimental settings, many researches have revealed the vulnerability of machine learning models caused by the violation of fundamental assumptions in real-wo...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166625 |