Date of Award
Spring 5-2018
Degree Type
Dissertation
Degree Name
Ph.D.
Degree Program
Engineering and Applied Science
Department
Electrical Engineering
Major Professor
AbdulRahman Alsamman
Second Advisor
Vesselin Jilkov
Third Advisor
Huimin Chen
Fourth Advisor
Martin Guillot
Fifth Advisor
Vassil Roussev
Abstract
Expert labeling, tagging, and assessment are far more costly than the processes of collecting raw data. Generative modeling is a very powerful tool to tackle this real-world problem. It is shown here how these models can be used to allow for semi-supervised learning that performs very well in label-deficient conditions.
The foundation for the work in this dissertation is built upon visualizing generative models' latent spaces to gain deeper understanding of data, analyze faults, and propose solutions. A number of novel ideas and approaches are presented to improve single-label classification. This dissertation's main focus is on extending semi-supervised Deep Generative Models for solving the multi-label problem by proposing unique mathematical and programming concepts and organization.
In all naive mixtures, using multiple labels is detrimental and causes each label's predictions to be worse than models that utilize only a single label. Examining latent spaces reveals that in many cases, large regions in the models generate meaningless results. Enforcing a priori independence is essential, and only when applied can multi-label models outperform the best single-label models. Finally, a novel learning technique called open-book learning is described that is capable of surpassing the state-of-the-art classification performance of generative models for multi-labeled, semi-supervised data sets.
Recommended Citation
Rastgoufard, Rastin, "Multi-Label Latent Spaces with Semi-Supervised Deep Generative Models" (2018). University of New Orleans Theses and Dissertations. 2486.
https://scholarworks.uno.edu/td/2486
Rights
The University of New Orleans and its agents retain the non-exclusive license to archive and make accessible this dissertation or thesis in whole or in part in all forms of media, now or hereafter known. The author retains all other ownership rights to the copyright of the thesis or dissertation.