서브메뉴
검색
Unsupervised Sleep-Like Processes for Enhancing Neural Networks
Unsupervised Sleep-Like Processes for Enhancing Neural Networks
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151118
- ISBN
- 9798383209257
- DDC
- 616
- 서명/저자
- Unsupervised Sleep-Like Processes for Enhancing Neural Networks
- 발행사항
- [Sl] : University of California, San Diego, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 102 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
- 주기사항
- Advisor: McAuley, Julian;Bazhenov, Maxim.
- 학위논문주기
- Thesis (Ph.D.)--University of California, San Diego, 2024.
- 초록/해제
- 요약Advancing our understanding of neuroscience and artificial intelligence, this dissertation aims to progress our understanding of memory representation, consolidation, and robustness within neural networks. While the brain serves as a remarkable inspiration for machine learning, our comprehension of its complexities remains limited. Gaining insight in how the brain operates enables mutual progress in both fields simultaneously, one potential avenue is through exploring sleep. Sleep is a significant yet only partially understood phenomena that occurs in biological brains. This critical physiological process is prevalent across species due to its pivotal role for many biologically relevant metabolic and cognitive functions; importantly sleep has been shown to be crucial for memory enhancement and consolidation. Despite the extreme importance of natural sleep, there is no true artificial counterpart in machine learning. This work elucidates the intricate mechanisms by which sleep enhances memory representation through biophysical modeling and applies these principals to a range of network architectures across the biophysical-artificial spectrum for a variety of tasks. Specifically, sleep mechanisms are conceptualized and illustrated in biophysical Hodgkin-Huxley neural networks capable of realistic wake and sleep activity. Similar sleep-like stages are then applied to map-based spiking neural networks to mitigate catastrophic forgetting in a sequential learning paradigm. Finally, fully bridging the neuroscience / artificial intelligence gap, a sleep based algorithm for artificial convolutional neural networks is proposed which bolsters the resilience of convolutional filters thereby improving model performance in distorted contexts. Collectively, this dissertation sheds light on the role of sleep in shaping memory across diverse neural systems and reimagines the relationship between artificial and biological intelligence.
- 일반주제명
- Neurosciences
- 일반주제명
- Computer science
- 일반주제명
- Bioinformatics
- 키워드
- Neural networks
- 키워드
- Machine learning
- 키워드
- Sleep mechanisms
- 키워드
- Robustness
- 기타저자
- University of California, San Diego Computer Science and Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-01B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160797
■00520250211151118
■006m o d
■007cr#unu||||||||
■020 ▼a9798383209257
■035 ▼a(MiAaPQ)AAI31145854
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616
■1001 ▼aDelanois, Jean Erik.
■24510▼aUnsupervised Sleep-Like Processes for Enhancing Neural Networks
■260 ▼a[Sl]▼bUniversity of California, San Diego▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a102 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-01, Section: B.
■500 ▼aAdvisor: McAuley, Julian;Bazhenov, Maxim.
■5021 ▼aThesis (Ph.D.)--University of California, San Diego, 2024.
■520 ▼aAdvancing our understanding of neuroscience and artificial intelligence, this dissertation aims to progress our understanding of memory representation, consolidation, and robustness within neural networks. While the brain serves as a remarkable inspiration for machine learning, our comprehension of its complexities remains limited. Gaining insight in how the brain operates enables mutual progress in both fields simultaneously, one potential avenue is through exploring sleep. Sleep is a significant yet only partially understood phenomena that occurs in biological brains. This critical physiological process is prevalent across species due to its pivotal role for many biologically relevant metabolic and cognitive functions; importantly sleep has been shown to be crucial for memory enhancement and consolidation. Despite the extreme importance of natural sleep, there is no true artificial counterpart in machine learning. This work elucidates the intricate mechanisms by which sleep enhances memory representation through biophysical modeling and applies these principals to a range of network architectures across the biophysical-artificial spectrum for a variety of tasks. Specifically, sleep mechanisms are conceptualized and illustrated in biophysical Hodgkin-Huxley neural networks capable of realistic wake and sleep activity. Similar sleep-like stages are then applied to map-based spiking neural networks to mitigate catastrophic forgetting in a sequential learning paradigm. Finally, fully bridging the neuroscience / artificial intelligence gap, a sleep based algorithm for artificial convolutional neural networks is proposed which bolsters the resilience of convolutional filters thereby improving model performance in distorted contexts. Collectively, this dissertation sheds light on the role of sleep in shaping memory across diverse neural systems and reimagines the relationship between artificial and biological intelligence.
■590 ▼aSchool code: 0033.
■650 4▼aNeurosciences
■650 4▼aComputer science
■650 4▼aBioinformatics
■653 ▼aNeural networks
■653 ▼aMachine learning
■653 ▼aBiological brains
■653 ▼aSleep mechanisms
■653 ▼aRobustness
■690 ▼a0800
■690 ▼a0317
■690 ▼a0984
■690 ▼a0715
■71020▼aUniversity of California, San Diego▼bComputer Science and Engineering.
■7730 ▼tDissertations Abstracts International▼g86-01B.
■790 ▼a0033
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160797▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
