東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Adaptation and Regularization of Dee...

Mutlu, Onur Cezmi,

Linked to FindBook

Google Book

Amazon

博客來

Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption // Onur Cezmi Mutlu.
Author:	Mutlu, Onur Cezmi,
Description:	1 electronic resource (86 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Graphs. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974587
ISBN:	9798311957151

Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption /
Mutlu, Onur Cezmi,

Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption /Onur Cezmi Mutlu. - 1 electronic resource (86 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

Deep neural networks have demonstrated exceptional performance across various machine learning tasks over the past decade, yet their deployment in resource-constrained and dynamically shifting real-world environments remains a challenge. While largescale models excel in accuracy, their computational demands often render them impractical for edge devices and real-time applications. In contrast, lightweight models, although efficient, frequently suffer from decreased robustness and generalization, particularly in dynamic settings that involve domain shifts. This trade-off is especially problematic in mobile healthcare applications, where privacy, efficiency, and reliability are critical constraints.This dissertation introduces TempT (Temporal Consistency for Test-Time Adaptation), a novel test-time adaptation (TTA) approach designed to enhance the robustness of deep neural networks without requiring labeled data. TempT leverages temporal coherence as a self-supervised learning signal, enforcing smoothness constraints on model predictions across sequential inputs. By minimizing high-frequency fluctuations, the method not only improves prediction stability but also enhances model performance and robustness in unseen environments. This adaptation technique is particularly effective in video-based learning tasks, such as facial expression recognition or video object detection, where maintaining consistency across frames is crucial.Furthermore, we explore the application of topological data analysis (TDA), particularly Persistent Homology, as a mechanism for quantifying model behavior during adaptation. By analyzing the topological features of intermediate network activations, we develop a selective adaptation strategy, enabling the model to determine when adaptation is beneficial and when it might degrade performance. Additionally, we propose a novel regularization technique based on temporal consistency, which mproves model generalization, and robustness against domain shifts.We evaluate our frameworks on real-world datasets, including AffWild2, SHIFT, and CIFAR100P. Experimental results demonstrate that TempT not only outperforms existing test-time adaptation methods, but also enables computationally efficient models to achieve performance levels comparable to larger, more expensive architectures. This work bridges the gap between domain adaptation and self-supervised learning, offering a robust, privacy-conscious, and scalable solution for deep learning in constrained environments.

English

ISBN: 9798311957151Subjects--Topical Terms:

3685259
Graphs.

Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption /
LDR:03815nmm a22003733i 4500 001 2433836
005 20250905091024.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798311957151
035 $a (MiAaPQD)AAI31974587
035 $a (MiAaPQD)Stanfordbp098kt2063
035 $a AAI31974587
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Mutlu, Onur Cezmi, $e author. $3 3823601
245 1 0 $a Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption / $c Onur Cezmi Mutlu.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (86 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
500 $a Advisors: Wall, Dennis Committee members: Nishimura, Dwight; Pauly, John.
502 $b Ph.D. $c Stanford University $d 2025.
520 $a Deep neural networks have demonstrated exceptional performance across various machine learning tasks over the past decade, yet their deployment in resource-constrained and dynamically shifting real-world environments remains a challenge. While largescale models excel in accuracy, their computational demands often render them impractical for edge devices and real-time applications. In contrast, lightweight models, although efficient, frequently suffer from decreased robustness and generalization, particularly in dynamic settings that involve domain shifts. This trade-off is especially problematic in mobile healthcare applications, where privacy, efficiency, and reliability are critical constraints.This dissertation introduces TempT (Temporal Consistency for Test-Time Adaptation), a novel test-time adaptation (TTA) approach designed to enhance the robustness of deep neural networks without requiring labeled data. TempT leverages temporal coherence as a self-supervised learning signal, enforcing smoothness constraints on model predictions across sequential inputs. By minimizing high-frequency fluctuations, the method not only improves prediction stability but also enhances model performance and robustness in unseen environments. This adaptation technique is particularly effective in video-based learning tasks, such as facial expression recognition or video object detection, where maintaining consistency across frames is crucial.Furthermore, we explore the application of topological data analysis (TDA), particularly Persistent Homology, as a mechanism for quantifying model behavior during adaptation. By analyzing the topological features of intermediate network activations, we develop a selective adaptation strategy, enabling the model to determine when adaptation is beneficial and when it might degrade performance. Additionally, we propose a novel regularization technique based on temporal consistency, which mproves model generalization, and robustness against domain shifts.We evaluate our frameworks on real-world datasets, including AffWild2, SHIFT, and CIFAR100P. Experimental results demonstrate that TempT not only outperforms existing test-time adaptation methods, but also enables computationally efficient models to achieve performance levels comparable to larger, more expensive architectures. This work bridges the gap between domain adaptation and self-supervised learning, offering a robust, privacy-conscious, and scalable solution for deep learning in constrained environments.
546 $a English
590 $a School code: 0212
650 4 $a Graphs. $3 3685259
650 4 $a Video recordings. $3 575241
650 4 $a Neural networks. $3 677449
650 4 $a Adaptation. $3 3562958
650 4 $a Fault tolerance. $3 3561030
650 4 $a Optimization algorithms. $3 3683616
650 4 $a Entropy. $3 546219
650 4 $a Computer science. $3 523869
690 $a 0984
690 $a 0800
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Wall, Dennis $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0212
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31974587