본문

서브메뉴

Temporal Intelligence in Spiking Neural Networks: A New Framework for Learning and Adaptation
Temporal Intelligence in Spiking Neural Networks: A New Framework for Learning and Adaptat...
Temporal Intelligence in Spiking Neural Networks: A New Framework for Learning and Adaptation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105528
ISBN  
9798263344979
DDC  
574
저자명  
Chakraborty, Biswadeep.
서명/저자  
Temporal Intelligence in Spiking Neural Networks: A New Framework for Learning and Adaptation
발행사항  
[Sl] : Georgia Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
259 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
주기사항  
Advisor: Mukhopadhyay, Saibal.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
초록/해제  
요약Artificial intelligence is at a crossroads: conventional deep learning models, while powerful, remain fundamentally limited in their ability to process information in time, adapt seamlessly to changing environments, and efficiently encode structured memory. The brain, by contrast, operates through spikes-discrete, event-driven signals that inherently capture temporal dependencies. Spiking Neural Networks (SNNs) have long been viewed primarily as energy-efficient alternatives to artificial neural networks (ANNs). This dissertation takes a fundamentally different view: it positions SNNs as a new computational paradigm, capable of expressing forms of temporal reasoning and adaptive intelligence that conventional deep learning struggles to achieve.However, realizing this vision requires overcoming a key limitation-most existing SNN models are built on homogeneous neuron and synapse dynamics, constraining their expressivity and adaptability. From a dynamical systems perspective, this homogeneity forces all neurons to evolve along similar timescales, reducing the network's ability to capture multi-scale dependencies and limiting the richness of its attractor landscape. By contrast, in complex dynamical systems-including the brain-heterogeneous timescales create diverse trajectories in state space, enhancing stability, memory capacity, and computational flexibility. To address this, this dissertation introduces Heterogeneous Recurrent Spiking Neural Networks (HRSNNs), a novel class of SNNs that leverage diverse neuronal and synaptic timescales to improve learning efficiency and temporal representation. By incorporating heterogeneity, HRSNNs enable structured memory retention, greater robustness to non-stationary inputs, and improved real-time adaptability.Yet, heterogeneity alone is insufficient to fully harness the computational power of SNNs. To systematically extract their unique advantages, this dissertation develops a new mathematical framework that bridges spike-based processing with dynamical systems theory, state-space models (SSMs), and Lyapunov stability analysis. These tools provide formal guarantees on stability, convergence, and learning efficiency, key properties that have remained elusive in SNN research. Additionally, this work proposes a task-agnostic pruning methodology, which sparsifies SNNs not based on task-specific heuristics, but by preserving key dynamical properties, allowing for efficient and generalizable representations. Beyond pruning, this dissertation extends SNNs to structured data and continuous domains through innovations such as Spiking Graph Neural Networks (SGNNs) and Spiking State-Space Models (S-SSMs), demonstrating their potential in real-world applications.Through applications spanning unsupervised learning, time-series prediction, multiagent interactions, and event-based perception, this dissertation reframes SNNs not as mere energy-efficient alternatives, but as a fundamentally new class of adaptive, real-time intelligent systems. By combining architectural innovations with deep theoretical insights, this work establishes a foundation for spike-based artificial intelligence that is not only efficient, but computationally powerful-offering a new perspective on how learning, memory, and intelligence can be reimagined through the lens of dynamical systems.
일반주제명  
Adaptation
일반주제명  
Neurons
일반주제명  
Energy efficiency
일반주제명  
Dynamical systems
일반주제명  
Neural networks
일반주제명  
System theory
일반주제명  
Mathematics
일반주제명  
Sustainability
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
■001000017360451
■00520260202105528
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263344979
■035    ▼a(MiAaPQ)AAI32309798
■035    ▼a(MiAaPQ)GeorgiaTech77821
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a574
■1001  ▼aChakraborty,  Biswadeep.
■24510▼aTemporal  Intelligence  in  Spiking  Neural  Networks:  A  New  Framework  for  Learning  and  Adaptation
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a259  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  A.
■500    ▼aAdvisor:  Mukhopadhyay,  Saibal.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2025.
■520    ▼aArtificial  intelligence  is  at  a  crossroads:  conventional  deep  learning  models,  while  powerful,  remain  fundamentally  limited  in  their  ability  to  process  information  in  time,  adapt  seamlessly  to  changing  environments,  and  efficiently  encode  structured  memory.  The  brain,  by  contrast,  operates  through  spikes-discrete,  event-driven  signals  that  inherently  capture  temporal  dependencies.  Spiking  Neural  Networks  (SNNs)  have  long  been  viewed  primarily  as  energy-efficient  alternatives  to  artificial  neural  networks  (ANNs).  This  dissertation  takes  a  fundamentally  different  view:  it  positions  SNNs  as  a  new  computational  paradigm,  capable  of  expressing  forms  of  temporal  reasoning  and  adaptive  intelligence  that  conventional  deep  learning  struggles  to  achieve.However,  realizing  this  vision  requires  overcoming  a  key  limitation-most  existing  SNN  models  are  built  on  homogeneous  neuron  and  synapse  dynamics,  constraining  their  expressivity  and  adaptability.  From  a  dynamical  systems  perspective,  this  homogeneity  forces  all  neurons  to  evolve  along  similar  timescales,  reducing  the  network's  ability  to  capture  multi-scale  dependencies  and  limiting  the  richness  of  its  attractor  landscape.  By  contrast,  in  complex  dynamical  systems-including  the  brain-heterogeneous  timescales  create  diverse  trajectories  in  state  space,  enhancing  stability,  memory  capacity,  and  computational  flexibility.  To  address  this,  this  dissertation  introduces  Heterogeneous  Recurrent  Spiking  Neural  Networks  (HRSNNs),  a  novel  class  of  SNNs  that  leverage  diverse  neuronal  and  synaptic  timescales  to  improve  learning  efficiency  and  temporal  representation.  By  incorporating  heterogeneity,  HRSNNs  enable  structured  memory  retention,  greater  robustness  to  non-stationary  inputs,  and  improved  real-time  adaptability.Yet,  heterogeneity  alone  is  insufficient  to  fully  harness  the  computational  power  of  SNNs.  To  systematically  extract  their  unique  advantages,  this  dissertation  develops  a  new  mathematical  framework  that  bridges  spike-based  processing  with  dynamical  systems  theory,  state-space  models  (SSMs),  and  Lyapunov  stability  analysis.  These  tools  provide  formal  guarantees  on  stability,  convergence,  and  learning  efficiency,  key  properties  that  have  remained  elusive  in  SNN  research.  Additionally,  this  work  proposes  a  task-agnostic  pruning  methodology,  which  sparsifies  SNNs  not  based  on  task-specific  heuristics,  but  by  preserving  key  dynamical  properties,  allowing  for  efficient  and  generalizable  representations.  Beyond  pruning,  this  dissertation  extends  SNNs  to  structured  data  and  continuous  domains  through  innovations  such  as  Spiking  Graph  Neural  Networks  (SGNNs)  and  Spiking  State-Space  Models  (S-SSMs),  demonstrating  their  potential  in  real-world  applications.Through  applications  spanning  unsupervised  learning,  time-series  prediction,  multiagent  interactions,  and  event-based  perception,  this  dissertation  reframes  SNNs  not  as  mere  energy-efficient  alternatives,  but  as  a  fundamentally  new  class  of  adaptive,  real-time  intelligent  systems.  By  combining  architectural  innovations  with  deep  theoretical  insights,  this  work  establishes  a  foundation  for  spike-based  artificial  intelligence  that  is  not  only  efficient,  but  computationally  powerful-offering  a  new  perspective  on  how  learning,  memory,  and  intelligence  can  be  reimagined  through  the  lens  of  dynamical  systems.
■590    ▼aSchool  code:  0078.
■650  4▼aAdaptation
■650  4▼aNeurons
■650  4▼aEnergy  efficiency
■650  4▼aDynamical  systems
■650  4▼aNeural  networks
■650  4▼aSystem  theory
■650  4▼aMathematics
■650  4▼aSustainability
■690    ▼a0800
■690    ▼a0405
■690    ▼a0640
■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=T17360451▼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
    TF17295 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.