{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/14437"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/14437","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies","abstract":"Deep learning based AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is safety. DNN models can become unreliable due to the uncertainty in data, e.g., insufficient labeled training data, measurement errors and noise in the label. To address this issue, Bayesian deep learning has become an appealing solution since it provides a mathematically grounded framework to quantify uncertainties for model's final prediction. As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs orders of magnitude higher computational costs than conventional DNN models, which poses a daunting challenge to traditional hardware platforms, such as CPUs/GPUs. The second issue lying in the conventional DNN applications is the laboring-intensive design period. The actual architecture design of a DNN model demands significant amount of efforts and cycles from machine learning experts. Fortunately, the recent emergence of Neural Architecture Search (NAS) has brought the neural architecture design into an era of automation. Nevertheless, the search cost is still prohibitively expensive for practical large-scale deployment in real-world applications. This dissertation focuses on designing high-speed and energy-efficient hardware accelerators for robust and automatic deep learning technologies, i.e. BNN and NAS. In this dissertation, two BNN accelerators, i.e., Fast-BCNN and Shift-BNN, are proposed to accelerate the BNN inference and training, respectively. Furthermore, an efficient in-situ NAS search engine is introduced for large-scale deployment in the real-world applications. The proposed accelerators show promise of solving the challenges during the execution of BNN and NAS workloads efficiently.","abstract_html":"Deep learning based AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is safety. DNN models can become unreliable due to the uncertainty in data, e.g., insufficient labeled training data, measurement errors and noise in the label. To address this issue, Bayesian deep learning has become an appealing solution since it provides a mathematically grounded framework to quantify uncertainties for model's final prediction. As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs orders of magnitude higher computational costs than conventional DNN models, which poses a daunting challenge to traditional hardware platforms, such as CPUs/GPUs. The second issue lying in the conventional DNN applications is the laboring-intensive design period. The actual architecture design of a DNN model demands significant amount of efforts and cycles from machine learning experts. Fortunately, the recent emergence of Neural Architecture Search (NAS) has brought the neural architecture design into an era of automation. Nevertheless, the search cost is still prohibitively expensive for practical large-scale deployment in real-world applications. This dissertation focuses on designing high-speed and energy-efficient hardware accelerators for robust and automatic deep learning technologies, i.e. BNN and NAS. In this dissertation, two BNN accelerators, i.e., Fast-BCNN and Shift-BNN, are proposed to accelerate the BNN inference and training, respectively. Furthermore, an efficient in-situ NAS search engine is introduced for large-scale deployment in the real-world applications. The proposed accelerators show promise of solving the challenges during the execution of BNN and NAS workloads efficiently.","abstract_has_math":false,"creators":["Wan, Qiyu"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":"Doctoral","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Fu, Xin"],"committee_chairs":[],"committee_members":["Rajashekara, Kaushik","Pan, Miao","Chen, Jinghong","Song, Shuaiwen Leon"],"year":2022,"date_issued":"2022-12-14","date_published":"2022-12-14","updated_at":"2026-07-24T02:33:06Z","subjects":["Hardware acceleration","Deep learning"],"languages":["eng"],"rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/14437","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Fu, Xin"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Rajashekara, Kaushik","Pan, Miao","Chen, Jinghong","Song, Shuaiwen Leon"]},{"key":"dc:creator","label":"Author","values":["Wan, Qiyu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-06-04T21:00:21Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-12-14"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hardware acceleration","Deep learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/14437"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Deep learning based AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is safety. DNN models can become unreliable due to the uncertainty in data, e.g., insufficient labeled training data, measurement errors and noise in the label. To address this issue, Bayesian deep learning has become an appealing solution since it provides a mathematically grounded framework to quantify uncertainties for model's final prediction. As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs orders of magnitude higher computational costs than conventional DNN models, which poses a daunting challenge to traditional hardware platforms, such as CPUs/GPUs. The second issue lying in the conventional DNN applications is the laboring-intensive design period. The actual architecture design of a DNN model demands significant amount of efforts and cycles from machine learning experts. Fortunately, the recent emergence of Neural Architecture Search (NAS) has brought the neural architecture design into an era of automation. Nevertheless, the search cost is still prohibitively expensive for practical large-scale deployment in real-world applications. This dissertation focuses on designing high-speed and energy-efficient hardware accelerators for robust and automatic deep learning technologies, i.e. BNN and NAS. In this dissertation, two BNN accelerators, i.e., Fast-BCNN and Shift-BNN, are proposed to accelerate the BNN inference and training, respectively. Furthermore, an efficient in-situ NAS search engine is introduced for large-scale deployment in the real-world applications. The proposed accelerators show promise of solving the challenges during the execution of BNN and NAS workloads efficiently."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies"]}]}],"canonical_facts":{"dc:contributor.advisor":["Fu, Xin"],"dc:contributor.committeemember":["Rajashekara, Kaushik","Pan, Miao","Chen, Jinghong","Song, Shuaiwen Leon"],"dc:creator":["Wan, Qiyu"],"dc:date.accessioned":["2023-06-04T21:00:21Z"],"dc:date.issued":["2022-12-14"],"dc:description.abstract":["Deep learning based AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is safety. DNN models can become unreliable due to the uncertainty in data, e.g., insufficient labeled training data, measurement errors and noise in the label. To address this issue, Bayesian deep learning has become an appealing solution since it provides a mathematically grounded framework to quantify uncertainties for model's final prediction. As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs orders of magnitude higher computational costs than conventional DNN models, which poses a daunting challenge to traditional hardware platforms, such as CPUs/GPUs. The second issue lying in the conventional DNN applications is the laboring-intensive design period. The actual architecture design of a DNN model demands significant amount of efforts and cycles from machine learning experts. Fortunately, the recent emergence of Neural Architecture Search (NAS) has brought the neural architecture design into an era of automation. Nevertheless, the search cost is still prohibitively expensive for practical large-scale deployment in real-world applications. This dissertation focuses on designing high-speed and energy-efficient hardware accelerators for robust and automatic deep learning technologies, i.e. BNN and NAS. In this dissertation, two BNN accelerators, i.e., Fast-BCNN and Shift-BNN, are proposed to accelerate the BNN inference and training, respectively. Furthermore, an efficient in-situ NAS search engine is introduced for large-scale deployment in the real-world applications. The proposed accelerators show promise of solving the challenges during the execution of BNN and NAS workloads efficiently."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/14437"],"dc:language.iso":["eng"],"dc:rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"dc:subject":["Hardware acceleration","Deep learning"],"dc:title":["Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:33:06Z"}