서브메뉴
검색
Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105508
- ISBN
- 9798263327002
- DDC
- 551.63
- 서명/저자
- Leveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
- 발행사항
- [Sl] : Georgia Institute of Technology, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 139 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
- 주기사항
- Advisor: Dovrolis, Constantine.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
- 초록/해제
- 요약Deep Neural Networks (DNNs) have transformed artificial intelligence, yet their success remains heavily dependent on large, static datasets, rigid architectures, and computationally intensive training processes. In contrast, biological brains excel in dynamic, resource-constrained environments. This thesis explores how principles from neuroscience can be abstracted and adapted to improve the adaptability and efficiency of modern deep learning systems. We propose three neuro-inspired methods that address key challenges in real-world machine learning: continual learning and data efficiency.First, we introduce NISPA, a method inspired by the brain's sparse dynamic connectivity and synaptic stability. Designed for task-incremental continual learning, NISPA preserves previously acquired knowledge by dynamically rewiring a sparse network and selectively freezing crucial connections. This approach significantly outperforms existing methods while requiring up to ten times fewer parameters.Second, we present NICE, a method inspired by adult neurogenesis and contextual memory encoding in the hippocampus. NICE eliminates the need for data replay in classincremental learning by grouping neurons according to their integration time into the network's function and using context detection to route inputs appropriately. Without storing or replaying past data, NICE matches-and often exceeds-the performance of popular replay-based methods while avoiding their computational overhead.Finally, we address efficient learning from streaming data with PEAKS, a method inspired by the brain's top-down attention mechanisms. PEAKS incrementally selects informative training samples based on prediction errors and kernel similarity, effectively filtering out noisy or redundant data. Our experiments show that PEAKS achieves competitive accuracy using as little as one-fourth the data compared to random selection.Collectively, these approaches demonstrate how neuro-inspired mechanisms-such as synaptic rewiring, contextual memory encoding, and attentional filtering-can substantially enhance the adaptability and efficiency of deep learning systems. They represent a step toward AI systems that are not only accurate but also resource-efficient, context-aware, and capable of lifelong learning.
- 일반주제명
- Skewness
- 일반주제명
- Neurons
- 일반주제명
- Deep learning
- 일반주제명
- Adaptability
- 일반주제명
- Memory
- 일반주제명
- Brain research
- 일반주제명
- Neural networks
- 일반주제명
- Seeds
- 일반주제명
- Neurogenesis
- 일반주제명
- Adaptation
- 일반주제명
- Design
- 일반주제명
- Neurosciences
- 일반주제명
- Agronomy
- 기본자료저록
- Dissertations Abstracts International. 87-05A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017360333
■00520260202105508
■006m o d
■007cr#unu||||||||
■020 ▼a9798263327002
■035 ▼a(MiAaPQ)AAI32308071
■035 ▼a(MiAaPQ)GeorgiaTech78646
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a551.63
■1001 ▼aGurbuz, Mustafa Burak.
■24510▼aLeveraging Neuro-Inspired Mechanisms for Adaptive and Efficient Deep Learning
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a139 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: A.
■500 ▼aAdvisor: Dovrolis, Constantine.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2025.
■520 ▼aDeep Neural Networks (DNNs) have transformed artificial intelligence, yet their success remains heavily dependent on large, static datasets, rigid architectures, and computationally intensive training processes. In contrast, biological brains excel in dynamic, resource-constrained environments. This thesis explores how principles from neuroscience can be abstracted and adapted to improve the adaptability and efficiency of modern deep learning systems. We propose three neuro-inspired methods that address key challenges in real-world machine learning: continual learning and data efficiency.First, we introduce NISPA, a method inspired by the brain's sparse dynamic connectivity and synaptic stability. Designed for task-incremental continual learning, NISPA preserves previously acquired knowledge by dynamically rewiring a sparse network and selectively freezing crucial connections. This approach significantly outperforms existing methods while requiring up to ten times fewer parameters.Second, we present NICE, a method inspired by adult neurogenesis and contextual memory encoding in the hippocampus. NICE eliminates the need for data replay in classincremental learning by grouping neurons according to their integration time into the network's function and using context detection to route inputs appropriately. Without storing or replaying past data, NICE matches-and often exceeds-the performance of popular replay-based methods while avoiding their computational overhead.Finally, we address efficient learning from streaming data with PEAKS, a method inspired by the brain's top-down attention mechanisms. PEAKS incrementally selects informative training samples based on prediction errors and kernel similarity, effectively filtering out noisy or redundant data. Our experiments show that PEAKS achieves competitive accuracy using as little as one-fourth the data compared to random selection.Collectively, these approaches demonstrate how neuro-inspired mechanisms-such as synaptic rewiring, contextual memory encoding, and attentional filtering-can substantially enhance the adaptability and efficiency of deep learning systems. They represent a step toward AI systems that are not only accurate but also resource-efficient, context-aware, and capable of lifelong learning.
■590 ▼aSchool code: 0078.
■650 4▼aSkewness
■650 4▼aNeurons
■650 4▼aDeep learning
■650 4▼aAdaptability
■650 4▼aMemory
■650 4▼aBrain research
■650 4▼aNeural networks
■650 4▼aSeeds
■650 4▼aNeurogenesis
■650 4▼aAdaptation
■650 4▼aDesign
■650 4▼aNeurosciences
■650 4▼aAgronomy
■690 ▼a0389
■690 ▼a0800
■690 ▼a0317
■690 ▼a0285
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05A.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360333▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


