본문

서브메뉴

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

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103135
ISBN  
9798311957151
DDC  
511.5
저자명  
Mutlu, Onur Cezmi.
서명/저자  
Adaptation and Regularization of Deep Neural Networks Under Temporal Smoothness Assumption
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
86 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
주기사항  
Advisor: Wall, Dennis.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Deep 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.
일반주제명  
Graphs
일반주제명  
Video recordings
일반주제명  
Neural networks
일반주제명  
Adaptation
일반주제명  
Fault tolerance
일반주제명  
Optimization algorithms
일반주제명  
Entropy
일반주제명  
Computer science
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357123
■00520260202103135
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798311957151
■035    ▼a(MiAaPQ)AAI31974587
■035    ▼a(MiAaPQ)Stanfordbp098kt2063
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a511.5
■1001  ▼aMutlu,  Onur  Cezmi.
■24510▼aAdaptation  and  Regularization  of  Deep  Neural  Networks  Under  Temporal  Smoothness  Assumption
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a86  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-12,  Section:  B.
■500    ▼aAdvisor:  Wall,  Dennis.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aDeep  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.
■590    ▼aSchool  code:  0212.
■650  4▼aGraphs
■650  4▼aVideo  recordings
■650  4▼aNeural  networks
■650  4▼aAdaptation
■650  4▼aFault  tolerance
■650  4▼aOptimization  algorithms
■650  4▼aEntropy
■650  4▼aComputer  science
■690    ▼a0984
■690    ▼a0800
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-12B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357123▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF16800 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.