Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


Ning_PhD_Dissertation_Final.pdf (8.83 MB)

ETD Abstract Container

Abstract Header

Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence

Xie, Ning
http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732

Abstract Details

2020, Doctor of Philosophy (PhD), Wright State University, Computer Science and Engineering PhD.
Deep Neural Networks (DNNs) are powerful tools blossomed in a variety of successful real-life applications. While the performance of DNNs is outstanding, their opaque nature raises a growing concern in the community, causing suspicions on the reliability and trustworthiness of decisions made by DNNs. In order to release such concerns and towards building reliable deep learning systems, research efforts are actively made in diverse aspects such as model interpretation, model fairness and bias, adversarial attacks and defenses, and so on. In this dissertation, we focus on the research topic of DNN interpretations for visual intelligence, aiming to unfold the black-box and provide explanations for visual intelligence tasks in a human-understandable way. We first conduct a categorized literature review, systematically introducing the realm of explainable deep learning. Following the review, two specific problems are tackled, explanations of Convolutions Neural Networks (CNNs), which relates the CNN decisions with input concepts, and interpretability of multi-model interactions, where an explainable model is built to solve a visual inference task. Visualization techniques are leveraged to depict the intermediate hidden states of CNNs and attention mechanisms are utilized to build an instinct explainable model. Towards increasing the trustworthiness of DNNs, a certainty measurement for decisions is also proposed as an extensive exploration of this study. To show how the introduced techniques holistically realize a contribution to interpretable and reliable deep neural networks for visual intelligence, further experiments and analyses are conducted for visual entailment task at the end of this dissertation.
Derek Doran, Ph.D. (Advisor)
Michael Raymer, Ph.D. (Committee Member)
Tanvi Banerjee, Ph.D. (Committee Member)
Pascal Hitzler, Ph.D. (Committee Member)
154 p.
Artificial Intelligence
Deep Neural Networks; DDNs; reliable deep learning system; reliable deep neural networks; visual intelligence; Convolutions Neural Networks

Recommended Citations

Citations

  • Xie, N. (2020). Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence [Doctoral dissertation, Wright State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732

    APA Style (7th edition)

  • Xie, Ning. Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence. 2020. Wright State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732.

    MLA Style (8th edition)

  • Xie, Ning. "Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence." Doctoral dissertation, Wright State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732

    Chicago Manual of Style (17th edition)

wright1596208422672732
249
© 2020, all rights reserved.
This open access ETD is published by Wright State University and OhioLINK.