서브메뉴
검색
Learning Brain Dynamics With Neural Operators
Learning Brain Dynamics With Neural Operators
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211150914
- ISBN
- 9798383565872
- DDC
- 616
- 서명/저자
- Learning Brain Dynamics With Neural Operators
- 발행사항
- [Sl] : Yale University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 162 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
- 주기사항
- Advisor: van Dijk, David;Cardin, Jessica.
- 학위논문주기
- Thesis (Ph.D.)--Yale University, 2024.
- 초록/해제
- 요약Understanding the intricate workings of the brain remains one of science's grand challenges. At its core, the brain operates as a dynamic system, with neural oscillations and coordinated activity patterns enabling integrated cognition. However, modeling these complex dynamics computationally has proven difficult. Traditional models often rely on restrictive assumptions about brain activity properties, limiting their utility. This thesis introduces innovative machine learning frameworks, utilizing neural operator techniques specifically designed for neural data, to model brain dynamics more effectively.Neural operators function as mappings between infinite-dimensional spaces, offering a flexible, data-driven approach to capture the complex spatiotemporal relationships in neural dynamics. This work presents four novel machine learning frameworks. The Neural Integro-Differential Equations (NIDEs) integrate instantaneous and temporal components, providing enhanced accuracy for complex systems like the brain. Attentional Neural Integral Equations ((A)NIEs) harness self-attention mechanisms to learn and compute unknown integral operators from data. The Continuous Spatiotemporal Transformers (CSTs) leverage a new Transformer architecture to model continuous systems directly from data, overcoming the limitations of traditional methods. Brain Language Models (BrainLMs) utilize extensive fMRI dataset pretraining and finetuning, offering unmatched versatility in modeling brain dynamics.Analyses of synthetic and real-world data validate these models' superior performance. NIDEs reveal the local and non-local effects of substances like ketamine on fMRI dynamics. (A)NIEs and CSTs demonstrate superior predictive capabilities in modeling fMRI and wide-field recordings, outperforming existing methods for learning dynamics. BrainLM efficiently identifies intrinsic functional networks and, through insilico perturbation analysis, showcases its ability to differentiate subject states using accumulated knowledge.Collectively, these advancements not only broaden the horizons of modeling diverse neural modalities and data types but also break free from the constraints of previous methodologies. The frameworks extend their utility to various dynamic modeling domains, enhancing flexibility. This thesis highlights the immense potential of AI in offering comprehensive insights and unraveling the organizational principles of complex systems, marking a significant stride in technology-driven neuroscience research.
- 일반주제명
- Neurosciences
- 일반주제명
- Computer science
- 일반주제명
- Physiology
- 일반주제명
- Medical imaging
- 키워드
- Machine learning
- 키워드
- Neural dynamics
- 키워드
- Neural operators
- 기타저자
- Yale University Neuroscience
- 기본자료저록
- Dissertations Abstracts International. 86-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160126
■00520250211150914
■006m o d
■007cr#unu||||||||
■020 ▼a9798383565872
■035 ▼a(MiAaPQ)AAI30812400
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616
■1001 ▼ade Oliveira Fonseca, Antonio Henrique.
■24510▼aLearning Brain Dynamics With Neural Operators
■260 ▼a[Sl]▼bYale University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a162 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-02, Section: B.
■500 ▼aAdvisor: van Dijk, David;Cardin, Jessica.
■5021 ▼aThesis (Ph.D.)--Yale University, 2024.
■520 ▼aUnderstanding the intricate workings of the brain remains one of science's grand challenges. At its core, the brain operates as a dynamic system, with neural oscillations and coordinated activity patterns enabling integrated cognition. However, modeling these complex dynamics computationally has proven difficult. Traditional models often rely on restrictive assumptions about brain activity properties, limiting their utility. This thesis introduces innovative machine learning frameworks, utilizing neural operator techniques specifically designed for neural data, to model brain dynamics more effectively.Neural operators function as mappings between infinite-dimensional spaces, offering a flexible, data-driven approach to capture the complex spatiotemporal relationships in neural dynamics. This work presents four novel machine learning frameworks. The Neural Integro-Differential Equations (NIDEs) integrate instantaneous and temporal components, providing enhanced accuracy for complex systems like the brain. Attentional Neural Integral Equations ((A)NIEs) harness self-attention mechanisms to learn and compute unknown integral operators from data. The Continuous Spatiotemporal Transformers (CSTs) leverage a new Transformer architecture to model continuous systems directly from data, overcoming the limitations of traditional methods. Brain Language Models (BrainLMs) utilize extensive fMRI dataset pretraining and finetuning, offering unmatched versatility in modeling brain dynamics.Analyses of synthetic and real-world data validate these models' superior performance. NIDEs reveal the local and non-local effects of substances like ketamine on fMRI dynamics. (A)NIEs and CSTs demonstrate superior predictive capabilities in modeling fMRI and wide-field recordings, outperforming existing methods for learning dynamics. BrainLM efficiently identifies intrinsic functional networks and, through insilico perturbation analysis, showcases its ability to differentiate subject states using accumulated knowledge.Collectively, these advancements not only broaden the horizons of modeling diverse neural modalities and data types but also break free from the constraints of previous methodologies. The frameworks extend their utility to various dynamic modeling domains, enhancing flexibility. This thesis highlights the immense potential of AI in offering comprehensive insights and unraveling the organizational principles of complex systems, marking a significant stride in technology-driven neuroscience research.
■590 ▼aSchool code: 0265.
■650 4▼aNeurosciences
■650 4▼aComputer science
■650 4▼aPhysiology
■650 4▼aMedical imaging
■653 ▼aComputational neuroscience
■653 ▼aData-driven algorithms
■653 ▼aMachine learning
■653 ▼aNeural dynamics
■653 ▼aNeural operators
■653 ▼aSpatiotemporal modeling
■690 ▼a0317
■690 ▼a0984
■690 ▼a0719
■690 ▼a0574
■71020▼aYale University▼bNeuroscience.
■7730 ▼tDissertations Abstracts International▼g86-02B.
■790 ▼a0265
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160126▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
