본문

서브메뉴

Understanding Dynamics in Intelligent Systems: Control and Learning in Neural Circuits and Artificial Neural Networks
Understanding Dynamics in Intelligent Systems: Control and Learning in Neural Circuits and...
Understanding Dynamics in Intelligent Systems: Control and Learning in Neural Circuits and Artificial Neural Networks

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105610
ISBN  
9798265427045
DDC  
574
저자명  
Chen, Feng.
서명/저자  
Understanding Dynamics in Intelligent Systems: Control and Learning in Neural Circuits and Artificial Neural Networks
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
263 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Druckmann, Shaul;Ganguli, Surya.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Intelligent systems, both neural circuits and artificial neural networks, rely on dynamical processes to enable computation, flexible adaptation and efficient learning. This dissertation explores these dynamical phenomena, revealing mechanisms that may subserve intelligence. In the first part, I will discuss neural dynamics recorded from biological experiments. A key subject of modern neuroscience is the adaptive control of behavior. Here, by analyzing and modeling neural dynamics in the orofacial motor cortex in Alston's singing mouse, we reveal a hierarchical mechanism of vocal production enabled by temporal scaling of the motor cortical dynamics. In complementary work on visual processing in Drosophila, we identify a recurrent neural circuit that dynamically sharpens temporal contrasts in visual inputs. Our modeling describes how recurrent dynamics can compensate for motion-induced blur, suggesting dynamic adaptation as an effective neural strategy for sensory enhancement. The second part examines iterative pruning in artificial neural networks through the lens of dynamics in the error landscape. We show that successive pruned networks remain connected by a linear path without error barriers, and that the subsequent retraining process can be interpreted as a form of thermalization that reshapes the weight distribution. The third part focuses on learning dynamics in artificial neural networks. We show that stochastic noise during training implicitly regularizes the learning trajectory towards simpler subnetworks, effectively reducing the model complexity and enhancing generalization. Additionally, we analyze how training dynamics impact performance in large language models. We find that conventional fine-tuning objective induces overconfidence, thereby limiting performance improvements when scaling test-time compute. We propose an alternative training method that aligns the training objective with the test-time strategy, achieving improved reasoning abilities. In summary, these studies highlight approaches to understand different critical roles of dynamics in intelligent systems and demonstrate how explaining the underlying mechanisms of dynamical processes can help advance our understanding of intelligence.
일반주제명  
Adaptation
일반주제명  
Insects
일반주제명  
Secondary schools
일반주제명  
Intelligent systems
일반주제명  
Teachers
일반주제명  
Neural networks
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360721
■00520260202105610
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265427045
■035    ▼a(MiAaPQ)AAI32316391
■035    ▼a(MiAaPQ)Stanfordff551mr4474
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a574
■1001  ▼aChen,  Feng.
■24510▼aUnderstanding  Dynamics  in  Intelligent  Systems:  Control  and  Learning  in  Neural  Circuits  and  Artificial  Neural  Networks
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a263  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Druckmann,  Shaul;Ganguli,  Surya.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aIntelligent  systems,  both  neural  circuits  and  artificial  neural  networks,  rely  on  dynamical  processes  to  enable  computation,  flexible  adaptation  and  efficient  learning.  This  dissertation  explores  these  dynamical  phenomena,  revealing  mechanisms  that  may  subserve  intelligence.  In  the  first  part,  I  will  discuss  neural  dynamics  recorded  from  biological  experiments.  A  key  subject  of  modern  neuroscience  is  the  adaptive  control  of  behavior.  Here,  by  analyzing  and  modeling  neural  dynamics  in  the  orofacial  motor  cortex  in  Alston's  singing  mouse,  we  reveal  a  hierarchical  mechanism  of  vocal  production  enabled  by  temporal  scaling  of  the  motor  cortical  dynamics.  In  complementary  work  on  visual  processing  in  Drosophila,  we  identify  a  recurrent  neural  circuit  that  dynamically  sharpens  temporal  contrasts  in  visual  inputs.  Our  modeling  describes  how  recurrent  dynamics  can  compensate  for  motion-induced  blur,  suggesting  dynamic  adaptation  as  an  effective  neural  strategy  for  sensory  enhancement.  The  second  part  examines  iterative  pruning  in  artificial  neural  networks  through  the  lens  of  dynamics  in  the  error  landscape.  We  show  that  successive  pruned  networks  remain  connected  by  a  linear  path  without  error  barriers,  and  that  the  subsequent  retraining  process  can  be  interpreted  as  a  form  of  thermalization  that  reshapes  the  weight  distribution.  The  third  part  focuses  on  learning  dynamics  in  artificial  neural  networks.  We  show  that  stochastic  noise  during  training  implicitly  regularizes  the  learning  trajectory  towards  simpler  subnetworks,  effectively  reducing  the  model  complexity  and  enhancing  generalization.  Additionally,  we  analyze  how  training  dynamics  impact  performance  in  large  language  models.  We  find  that  conventional  fine-tuning  objective  induces  overconfidence,  thereby  limiting  performance  improvements  when  scaling  test-time  compute.  We  propose  an  alternative  training  method  that  aligns  the  training  objective  with  the  test-time  strategy,  achieving  improved  reasoning  abilities.  In  summary,  these  studies  highlight  approaches  to  understand  different  critical  roles  of  dynamics  in  intelligent  systems  and  demonstrate  how  explaining  the  underlying  mechanisms  of  dynamical  processes  can  help  advance  our  understanding  of  intelligence.
■590    ▼aSchool  code:  0212.
■650  4▼aAdaptation
■650  4▼aInsects
■650  4▼aSecondary  schools
■650  4▼aIntelligent  systems
■650  4▼aTeachers
■650  4▼aNeural  networks
■690    ▼a0800
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360721▼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
    TF17654 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.