본문

서브메뉴

Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105508
ISBN  
9798263327002
DDC  
551.63
저자명  
Gurbuz, Mustafa Burak.
서명/저자  
Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
발행사항  
[Sl] : Georgia Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
139 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
주기사항  
Advisor: Dovrolis, Constantine.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
초록/해제  
요약Deep Neural Networks (DNNs) have transformed artificial intelligence, yet their success remains heavily dependent on large, static datasets, rigid architectures, and computationally intensive training processes. In contrast, biological brains excel in dynamic, resource-constrained environments. This thesis explores how principles from neuroscience can be abstracted and adapted to improve the adaptability and efficiency of modern deep learning systems. We propose three neuro-inspired methods that address key challenges in real-world machine learning: continual learning and data efficiency.First, we introduce NISPA, a method inspired by the brain's sparse dynamic connectivity and synaptic stability. Designed for task-incremental continual learning, NISPA preserves previously acquired knowledge by dynamically rewiring a sparse network and selectively freezing crucial connections. This approach significantly outperforms existing methods while requiring up to ten times fewer parameters.Second, we present NICE, a method inspired by adult neurogenesis and contextual memory encoding in the hippocampus. NICE eliminates the need for data replay in classincremental learning by grouping neurons according to their integration time into the network's function and using context detection to route inputs appropriately. Without storing or replaying past data, NICE matches-and often exceeds-the performance of popular replay-based methods while avoiding their computational overhead.Finally, we address efficient learning from streaming data with PEAKS, a method inspired by the brain's top-down attention mechanisms. PEAKS incrementally selects informative training samples based on prediction errors and kernel similarity, effectively filtering out noisy or redundant data. Our experiments show that PEAKS achieves competitive accuracy using as little as one-fourth the data compared to random selection.Collectively, these approaches demonstrate how neuro-inspired mechanisms-such as synaptic rewiring, contextual memory encoding, and attentional filtering-can substantially enhance the adaptability and efficiency of deep learning systems. They represent a step toward AI systems that are not only accurate but also resource-efficient, context-aware, and capable of lifelong learning.
일반주제명  
Skewness
일반주제명  
Neurons
일반주제명  
Deep learning
일반주제명  
Adaptability
일반주제명  
Memory
일반주제명  
Brain research
일반주제명  
Neural networks
일반주제명  
Seeds
일반주제명  
Neurogenesis
일반주제명  
Adaptation
일반주제명  
Design
일반주제명  
Neurosciences
일반주제명  
Agronomy
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360333
■00520260202105508
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263327002
■035    ▼a(MiAaPQ)AAI32308071
■035    ▼a(MiAaPQ)GeorgiaTech78646
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a551.63
■1001  ▼aGurbuz,  Mustafa  Burak.
■24510▼aLeveraging  Neuro-Inspired  Mechanisms  for  Adaptive  and  Efficient  Deep  Learning
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a139  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  A.
■500    ▼aAdvisor:  Dovrolis,  Constantine.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2025.
■520    ▼aDeep  Neural  Networks  (DNNs)  have  transformed  artificial  intelligence,  yet  their  success  remains  heavily  dependent  on  large,  static  datasets,  rigid  architectures,  and  computationally  intensive  training  processes.  In  contrast,  biological  brains  excel  in  dynamic,  resource-constrained  environments.  This  thesis  explores  how  principles  from  neuroscience  can  be  abstracted  and  adapted  to  improve  the  adaptability  and  efficiency  of  modern  deep  learning  systems.  We  propose  three  neuro-inspired  methods  that  address  key  challenges  in  real-world  machine  learning:  continual  learning  and  data  efficiency.First,  we  introduce  NISPA,  a  method  inspired  by  the  brain's  sparse  dynamic  connectivity  and  synaptic  stability.  Designed  for  task-incremental  continual  learning,  NISPA  preserves  previously  acquired  knowledge  by  dynamically  rewiring  a  sparse  network  and  selectively  freezing  crucial  connections.  This  approach  significantly  outperforms  existing  methods  while  requiring  up  to  ten  times  fewer  parameters.Second,  we  present  NICE,  a  method  inspired  by  adult  neurogenesis  and  contextual  memory  encoding  in  the  hippocampus.  NICE  eliminates  the  need  for  data  replay  in  classincremental  learning  by  grouping  neurons  according  to  their  integration  time  into  the  network's  function  and  using  context  detection  to  route  inputs  appropriately.  Without  storing  or  replaying  past  data,  NICE  matches-and  often  exceeds-the  performance  of  popular  replay-based  methods  while  avoiding  their  computational  overhead.Finally,  we  address  efficient  learning  from  streaming  data  with  PEAKS,  a  method  inspired  by  the  brain's  top-down  attention  mechanisms.  PEAKS  incrementally  selects  informative  training  samples  based  on  prediction  errors  and  kernel  similarity,  effectively  filtering  out  noisy  or  redundant  data.  Our  experiments  show  that  PEAKS  achieves  competitive  accuracy  using  as  little  as  one-fourth  the  data  compared  to  random  selection.Collectively,  these  approaches  demonstrate  how  neuro-inspired  mechanisms-such  as  synaptic  rewiring,  contextual  memory  encoding,  and  attentional  filtering-can  substantially  enhance  the  adaptability  and  efficiency  of  deep  learning  systems.  They  represent  a  step  toward  AI  systems  that  are  not  only  accurate  but  also  resource-efficient,  context-aware,  and  capable  of  lifelong  learning.
■590    ▼aSchool  code:  0078.
■650  4▼aSkewness
■650  4▼aNeurons
■650  4▼aDeep  learning
■650  4▼aAdaptability
■650  4▼aMemory
■650  4▼aBrain  research
■650  4▼aNeural  networks
■650  4▼aSeeds
■650  4▼aNeurogenesis
■650  4▼aAdaptation
■650  4▼aDesign
■650  4▼aNeurosciences
■650  4▼aAgronomy
■690    ▼a0389
■690    ▼a0800
■690    ▼a0317
■690    ▼a0285
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05A.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360333▼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
    TF19142 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.