서브메뉴
검색
Modular Learning Systems for Continual Control: Neural Principles and Computational Models
Modular Learning Systems for Continual Control: Neural Principles and Computational Models
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105116
- ISBN
- 9798291575284
- DDC
- 616
- 서명/저자
- Modular Learning Systems for Continual Control: Neural Principles and Computational Models
- 발행사항
- [Sl] : Columbia University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 170 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: A.
- 주기사항
- Advisor: Abbott, Larry F.;Churchland, Mark M.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2025.
- 초록/해제
- 요약How do animals learn flexible behaviors that generalize across time, context, and perturbation? This thesis addresses this question through a unified framework that links normative theories of control, neural population dynamics, and learning algorithms.Chapter 2: A Framework for Motor Control introduces a probabilistic framework for motor control that unifies principles from optimal feedback control and dynamical systems theory. By casting control as inference in a latent dynamical system, I show that internal memory dynamics and sensory feedback jointly support adaptive, feedback-sensitive motor behavior. The resulting model naturally reproduces hallmark features of biological control-including preparatory activity, feedback corrections, and orthogonal subspaces-while implementing a soft form of model predictive control. Chapter 3: Continuous Behavior from Distinct Skills: Compositionality in Motor Cortex tests these theoretical predictions in motor cortex recordings from non-human primates performing a continuous force-tracking task. I find that motor cortex activity transitions from a condition-invariant preparatory regime to a dynamic execution regime, and that feedback perturbations engage the preparatory subspace even during movement. These findings provide empirical support for a re-planning interpretation of feedback-based correction and demonstrate that motor cortex flexibly deploys distinct neural subspaces to support planning and execution.Chapter 4: Dual-Learning for Supervised Learning builds on this framework to address a central challenge in training large neural networks: how to balance fast, efficient learning with stability and long-term retention. I derive a theoretical bound on the maximum stable learning rate that explicitly captures the interaction between curvature and gradient noise. Motivated by this bound, I propose a dual-learning architecture in which a fast low-rank learner adapts quickly while a slow full-rank module consolidates long-term knowledge. This architecture enables efficient, robust learning, supports continual task acquisition, and aligns with biological motifs observed in thalamocortical loops.Together, these studies advance a unified view of flexible motor behavior-one that integrates control, learning, and neurobiology-and lay the groundwork for scalable algorithms that mirror the brain's capacity for adaptation and generalization.
- 일반주제명
- Neurosciences
- 일반주제명
- Physiology
- 일반주제명
- Computer engineering
- 일반주제명
- Information science
- 키워드
- Neural networks
- 키워드
- Motor cortex
- 기타저자
- Columbia University Neurobiology and Behavior
- 기본자료저록
- Dissertations Abstracts International. 87-02A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359415
■00520260202105116
■006m o d
■007cr#unu||||||||
■020 ▼a9798291575284
■035 ▼a(MiAaPQ)AAI32237461
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616
■1001 ▼aAmematsro, Elom A.
■24510▼aModular Learning Systems for Continual Control: Neural Principles and Computational Models
■260 ▼a[Sl]▼bColumbia University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a170 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: A.
■500 ▼aAdvisor: Abbott, Larry F.;Churchland, Mark M.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2025.
■520 ▼aHow do animals learn flexible behaviors that generalize across time, context, and perturbation? This thesis addresses this question through a unified framework that links normative theories of control, neural population dynamics, and learning algorithms.Chapter 2: A Framework for Motor Control introduces a probabilistic framework for motor control that unifies principles from optimal feedback control and dynamical systems theory. By casting control as inference in a latent dynamical system, I show that internal memory dynamics and sensory feedback jointly support adaptive, feedback-sensitive motor behavior. The resulting model naturally reproduces hallmark features of biological control-including preparatory activity, feedback corrections, and orthogonal subspaces-while implementing a soft form of model predictive control. Chapter 3: Continuous Behavior from Distinct Skills: Compositionality in Motor Cortex tests these theoretical predictions in motor cortex recordings from non-human primates performing a continuous force-tracking task. I find that motor cortex activity transitions from a condition-invariant preparatory regime to a dynamic execution regime, and that feedback perturbations engage the preparatory subspace even during movement. These findings provide empirical support for a re-planning interpretation of feedback-based correction and demonstrate that motor cortex flexibly deploys distinct neural subspaces to support planning and execution.Chapter 4: Dual-Learning for Supervised Learning builds on this framework to address a central challenge in training large neural networks: how to balance fast, efficient learning with stability and long-term retention. I derive a theoretical bound on the maximum stable learning rate that explicitly captures the interaction between curvature and gradient noise. Motivated by this bound, I propose a dual-learning architecture in which a fast low-rank learner adapts quickly while a slow full-rank module consolidates long-term knowledge. This architecture enables efficient, robust learning, supports continual task acquisition, and aligns with biological motifs observed in thalamocortical loops.Together, these studies advance a unified view of flexible motor behavior-one that integrates control, learning, and neurobiology-and lay the groundwork for scalable algorithms that mirror the brain's capacity for adaptation and generalization.
■590 ▼aSchool code: 0054.
■650 4▼aNeurosciences
■650 4▼aPhysiology
■650 4▼aComputer engineering
■650 4▼aInformation science
■653 ▼aLearning algorithms
■653 ▼aContinual task acquisition
■653 ▼aNeural networks
■653 ▼aMotor cortex
■690 ▼a0317
■690 ▼a0464
■690 ▼a0723
■690 ▼a0719
■71020▼aColumbia University▼bNeurobiology and Behavior.
■7730 ▼tDissertations Abstracts International▼g87-02A.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359415▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
