University of South Florida
Deep Learning Enhancement and Privacy-Preserving Deep Learning: A Data-Centric Approach
Abstract
dc:descriptionDeep Learning and its applications have become attractive to a lot of research recentlybecause of its capability to capture important information from large amounts of data. While most of the work focuses on finding the best model parameters, improving machine learning performance from data perspective still needs more attention. In this work, we propose techniques to enhance the robustness of deep learning classification by tackling data issue. Specifically, our data processing proposals aim to alleviate the impacts of class-imbalanced data and non- IID data in deep learning classification and federated learning scenarios. In addition, data pre-processing strategies such that dimensionality reduction is also enhanced using a proposed deep learning-based technique for a scenario of data privacy preservation. By conducting several experiments and comparisons, we show that our approaches yield good performance and constantly outperform many state-of-the-art methods.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy (Ph.D.)
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Electrical Engineering
- Grantor
- University of South Florida
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Nguyen, Hung S.
- Contributors dc:contributor
-
- Chang J. Morris, Ph.D.
- Ismail Uysal, Ph.D.
- Zhuo Lu, Ph.D.
- Lu Lu, Ph.D.
- Simon Ou, Ph.D.
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.usf.edu/etd/9989