본문

서브메뉴

Neural Network Models of Learning and Generalization
Neural Network Models of Learning and Generalization
Neural Network Models of Learning and Generalization

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104750
ISBN  
9798290657219
DDC  
330
저자명  
Vafeidis, Panteleimon.
서명/저자  
Neural Network Models of Learning and Generalization
발행사항  
[Sl] : California Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
250 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Rangel, Antonio.
학위논문주기  
Thesis (Ph.D.)--California Institute of Technology, 2025.
초록/해제  
요약Neural networks have emerged as powerful models for understanding both biological and artificial intelligence, yet significant questions remain about how these systems develop rich, generalizable representations of the world. This thesis investigates fundamental principles of learning and generalization across four interconnected domains, bridging insights from theoretical neuroscience and artificial intelligence to advance our understanding of intelligent systems.In Chapter I, we address a central question in associative learning: how do neural circuits learn to associate concepts with one another? We propose a recurrent neural network model incorporating two critical features of cortical architecture-mixed selectivity and compartmentalized neurons. These architectural inductive biases enable a biologically plausible learning rule that achieves stimulus substitution, where neurons respond identically to a conditioned stimulus as they would to the associated unconditioned stimulus. Our model explains a remarkable range of conditioning phenomena under conditions in which traditional associative models fail, highlighting how the cortical architecture may confer significant evolutionary advantages for flexible learning.Chapter II pivots from the static mappings between concepts learned in Chapter I to explore how neural systems develop the precise synaptic connectivity required to establish dynamic mappings for path integration-the ability to maintain an internal sense of direction without external cues. We demonstrate that the same principles of compartmentalized learning can shape networks that accurately track angular position in darkness. Applied to the Drosophilahead direction system, our model develops connectivity patterns strikingly similar to those observed experimentally, with continuous attractor (CAN) dynamics emerging naturally from learning. This offers a novel perspective on how precisely calibrated neural circuits can develop through experience, rather than requiring genetic pre-specification, and explains experimental findings where animals adapt their internal representation when sensory experience changes.In Chapter III, we establish a theoretical framework explaining how disentangled representations-internal models that isolate independent factors of variation in the world-emerge from multi-task learning. We prove that any system competent at multiple related tasks must implicitly represent the underlying latent variables in a linearly decodable form when sufficient tasks are learned. These theoretical guarantees align with experimental results showing neural networks develop generalizable representations when trained on multiple tasks simultaneously. This work reveals a fundamental connection between task diversity and representation quality, with implications for biological cognition and artificial intelligence design, particularly explaining why modern transformer models may develop human-interpretable concepts, and how brains may acquire their impressive zero-shot generalization ability.Chapter IV proposes leveraging Large Language Models as cognitive tools for evaluating latent factor hypotheses for psychology, leveraging the theoretical insights from Chapter III. It suggests that the self-consistency of an LLM's responses given hypothesized psychological factors could serve as a metric for hypothesis evaluation. While preliminary, this approach represents a novel computational methodology for psychology that could transform how hypotheses for human cognition are developed and refined.All chapters are supported by corresponding Appendices that go deeper in particular details, including proofs. An exemption is Chapter IV, which is work early in development (yet valuable to mention). Instead, for Appendix D we provide some considerations about the detection of Continuous Attractors (CANs), which display prominently in Chapters II and III, consideration particularly important in order to avoid confusion when it comes to these concepts, particularly within the experimental neuroscience community.Together, these investigations reveal complementary aspects of how intelligent systems develop useful representations through learning. From biologically plausible learning rules to abstract computational principles, this thesis demonstrates how neural networks can illuminate fundamental mechanisms of intelligence across natural and artificial systems, advancing our understanding of the computational foundations that enable flexible, generalizable learning.
일반주제명  
Sparsity
일반주제명  
Neurosciences
일반주제명  
Neural networks
기타저자  
California Institute of Technology Biology and Biological Engineering
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358779
■00520260202104750
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290657219
■035    ▼a(MiAaPQ)AAI32151333
■035    ▼a(MiAaPQ)Caltech17258
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a330
■1001  ▼aVafeidis,  Panteleimon.
■24510▼aNeural  Network  Models  of  Learning  and  Generalization
■260    ▼a[Sl]▼bCalifornia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a250  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Rangel,  Antonio.
■5021  ▼aThesis  (Ph.D.)--California  Institute  of  Technology,  2025.
■520    ▼aNeural  networks  have  emerged  as  powerful  models  for  understanding  both  biological  and  artificial  intelligence,  yet  significant  questions  remain  about  how  these  systems  develop  rich,  generalizable  representations  of  the  world.  This  thesis  investigates  fundamental  principles  of  learning  and  generalization  across  four  interconnected  domains,  bridging  insights  from  theoretical  neuroscience  and  artificial  intelligence  to  advance  our  understanding  of  intelligent  systems.In  Chapter  I,  we  address  a  central  question  in  associative  learning:  how  do  neural  circuits  learn  to  associate  concepts  with  one  another?  We  propose  a  recurrent  neural  network  model  incorporating  two  critical  features  of  cortical  architecture-mixed  selectivity  and  compartmentalized  neurons.  These  architectural  inductive  biases  enable  a  biologically  plausible  learning  rule  that  achieves  stimulus  substitution,  where  neurons  respond  identically  to  a  conditioned  stimulus  as  they  would  to  the  associated  unconditioned  stimulus.  Our  model  explains  a  remarkable  range  of  conditioning  phenomena  under  conditions  in  which  traditional  associative  models  fail,  highlighting  how  the  cortical  architecture  may  confer  significant  evolutionary  advantages  for  flexible  learning.Chapter  II  pivots  from  the  static  mappings  between  concepts  learned  in  Chapter  I  to  explore  how  neural  systems  develop  the  precise  synaptic  connectivity  required  to  establish  dynamic  mappings  for  path  integration-the  ability  to  maintain  an  internal  sense  of  direction  without  external  cues.  We  demonstrate  that  the  same  principles  of  compartmentalized  learning  can  shape  networks  that  accurately  track  angular  position  in  darkness.  Applied  to  the  Drosophilahead  direction  system,  our  model  develops  connectivity  patterns  strikingly  similar  to  those  observed  experimentally,  with  continuous  attractor  (CAN)  dynamics  emerging  naturally  from  learning.  This  offers  a  novel  perspective  on  how  precisely  calibrated  neural  circuits  can  develop  through  experience,  rather  than  requiring  genetic  pre-specification,  and  explains  experimental  findings  where  animals  adapt  their  internal  representation  when  sensory  experience  changes.In  Chapter  III,  we  establish  a  theoretical  framework  explaining  how  disentangled  representations-internal  models  that  isolate  independent  factors  of  variation  in  the  world-emerge  from  multi-task  learning.  We  prove  that  any  system  competent  at  multiple  related  tasks  must  implicitly  represent  the  underlying  latent  variables  in  a    linearly  decodable  form  when  sufficient  tasks  are  learned.  These  theoretical  guarantees  align  with  experimental  results  showing  neural  networks  develop  generalizable  representations  when  trained  on  multiple  tasks  simultaneously.  This  work  reveals  a  fundamental  connection  between  task  diversity  and  representation  quality,  with  implications  for  biological  cognition  and  artificial  intelligence  design,  particularly  explaining  why  modern  transformer  models  may  develop  human-interpretable  concepts,  and  how  brains  may  acquire  their  impressive  zero-shot  generalization  ability.Chapter  IV  proposes  leveraging  Large  Language  Models  as  cognitive  tools  for  evaluating  latent  factor  hypotheses  for  psychology,  leveraging  the  theoretical  insights  from  Chapter  III.  It  suggests  that  the  self-consistency  of  an  LLM's  responses  given  hypothesized  psychological  factors  could  serve  as  a  metric  for  hypothesis  evaluation.  While  preliminary,  this  approach  represents  a  novel  computational  methodology  for  psychology  that  could  transform  how  hypotheses  for  human  cognition  are  developed  and  refined.All  chapters  are  supported  by  corresponding  Appendices  that  go  deeper  in  particular  details,  including  proofs.  An  exemption  is  Chapter  IV,  which  is  work  early  in  development  (yet  valuable  to  mention).  Instead,  for  Appendix  D  we  provide  some  considerations  about  the  detection  of  Continuous  Attractors  (CANs),  which  display  prominently  in  Chapters  II  and  III,  consideration  particularly  important  in  order  to  avoid  confusion  when  it  comes  to  these  concepts,  particularly  within  the  experimental  neuroscience  community.Together,  these  investigations  reveal  complementary  aspects  of  how  intelligent  systems  develop  useful  representations  through  learning.  From  biologically  plausible  learning  rules  to  abstract  computational  principles,  this  thesis  demonstrates  how  neural  networks  can  illuminate  fundamental  mechanisms  of  intelligence  across  natural  and  artificial  systems,  advancing  our  understanding  of  the  computational  foundations  that  enable  flexible,  generalizable  learning.
■590    ▼aSchool  code:  0037.
■650  4▼aSparsity
■650  4▼aNeurosciences
■650  4▼aNeural  networks
■690    ▼a0800
■690    ▼a0317
■71020▼aCalifornia  Institute  of  Technology▼bBiology  and  Biological  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0037
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358779▼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
    TF19403 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.