Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence

Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence

Bibliographic Details
Main Author: Xie, Ning
Language:English
Published: Wright State University / OhioLINK 2020
Subjects:
Artificial Intelligence
Deep Neural Networks
DDNs
reliable deep learning system
reliable deep neural networks
visual intelligence
Convolutions Neural Networks
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732
id ndltd-OhioLink-oai-etd.ohiolink.edu-wright1596208422672732
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-wright15962084226727322021-08-07T05:10:13Z Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence Xie, Ning Artificial Intelligence Deep Neural Networks DDNs reliable deep learning system reliable deep neural networks visual intelligence Convolutions Neural Networks 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. 2020-08-06 English text Wright State University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732 http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
collection NDLTD
language English
sources NDLTD
topic Artificial Intelligence
Deep Neural Networks
DDNs
reliable deep learning system
reliable deep neural networks
visual intelligence
Convolutions Neural Networks
spellingShingle Artificial Intelligence
Deep Neural Networks
DDNs
reliable deep learning system
reliable deep neural networks
visual intelligence
Convolutions Neural Networks
Xie, Ning
Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
author Xie, Ning
author_facet Xie, Ning
author_sort Xie, Ning
title Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
title_short Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
title_full Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
title_fullStr Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
title_full_unstemmed Towards Interpretable and Reliable Deep Neural Networks for Visual Intelligence
title_sort towards interpretable and reliable deep neural networks for visual intelligence
publisher Wright State University / OhioLINK
publishDate 2020
url http://rave.ohiolink.edu/etdc/view?acc_num=wright1596208422672732
work_keys_str_mv AT xiening towardsinterpretableandreliabledeepneuralnetworksforvisualintelligence
_version_ 1719458786540781568

Similar Items