Author ORCID Identifier
Semester
Spring
Date of Graduation
2024
Document Type
Dissertation
Degree Type
PhD
College
Statler College of Engineering and Mineral Resources
Department
Lane Department of Computer Science and Electrical Engineering
Committee Chair
Donald Adjeroh
Committee Member
Nasser Nasrabadi
Committee Member
Jeremy Dawson
Committee Member
Gianfranco Doretto
Committee Member
Michael Hu
Abstract
The primary goal of this dissertation is to investigate and improve the efficiency of deep learning algorithms, especially within computer vision problem domains, from the perspective of label-efficiency. This investigation showed that deep learning algorithms are mostly notorious for the lack of uncertainty representation. Accordingly, we aimed to develop an array of deep learning frameworks rich with uncertainty representation. These frameworks are mainly within two current pillars of machine learning, deep active learning and self-supervised learning. These frameworks include deep active ensemble sampling for efficient sample selection within deep active learning, a two-stage ensemble-based general self-training approach for existing visual self-supervised learning baselines, introduction of partial information decomposition to self-supervised learning and developing two techniques to exploit synergistic and unique information component within PID context, and a coloring approach for enhanced feature decoupling within self-supervised feature learning. Along with this major line of work, we also investigated the application of computational methods (e.g., machine learning and signal processing algorithms) in some problems in computational biology. This included applications in human genome sequence modeling, age estimation using gene expression data, age-related gene selection, and causal inference and association for age-related genes. Taken all these together, this dissertation shed insight on label-efficiency in deep learning, the efficient use of scarce data and resources (such as the case with computational biology), and on recent directions in generative AI.
Recommended Citation
Mohamadi, Salman, "Active Uncertainty Representation Learning: Toward More Label Efficiency in Deep Learning" (2024). Graduate Theses, Dissertations, and Problem Reports. 12295.
https://researchrepository.wvu.edu/etd/12295