全部 |
  • 全部
  • 题名
  • 关键词
  • NSTL主题词
  • 摘要
  • 会议名称
  • 论文-出处
  • 论文-作者
  • 论文-机构
  • 论文-DOI
  • 会议-出版者
  • 会议-出版地
  • 会议-主编
  • 会议-主办单位
  • 会议-举办地
  • ISSN
  • EISSN
  • ISBN
  • EISBN
检索 搜索会议录 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. Optoelectronic integrated neuromorphic devices towards vision perception NSTL国家科技图书文献中心

Qiang Wang |  Lifeng Liu... -  《Tenth Symposium on Novel Optoelectronic Detection Technology and Applications,Part One of Three Parts》 -  Symposium on Novel Optoelectronic Detection Technology and Applications - 2025, - 135110N.1~135110N.7 - 共7页

摘要: integrated device with in-memory sensing and computing is |  neuromorphic devices with in-memory sensing and computing was |  photoelectric conversion and memory. Optoelectronic integrated |  preparations. In the current study, towards the large-scale |  detectors and non-volatile memristors. In addition, the
关键词: Vision perception |  Optoelectronic integrated neuromorphic devices |  Resistive random access memory |  Photodetectors

2. Task prioritization offloading scheme for vehicular edge computing networks: a game-theoretic DRL approach NSTL国家科技图书文献中心

Jiaojiao Sun |  Li Jiang... -  《Fourth International Conference on Computer Vision,Application,and Algorithm (CVAA 2024)》 -  International Conference on Computer Vision,Application,and Algorithm - 2025, - 134862X.1~134862X.8 - 共8页

摘要: Computing (VEC) computing architectures, in the study of |  task offloading problem, based on the differences in | -cooperative game, and introduces a memory mechanism (RNN |  Actor-Critic) in the MADDPG algorithm, which improves | With the development of Vehicular Edge
关键词: Task offloading |  Deep reinforcement learning |  Game theory |  Delayed classification

3. Comparing Training of Sparse to Classic Neural Networks for Binary Classification in Medical Data NSTL国家科技图书文献中心

Laura Erhan |  Antonio Liotta... -  《Advances in Mobile Computing and Multimedia Intelligence》 -  International Conference on Advances in Mobile Computing and Multimedia Intelligence - 2025, - 101~106 - 共6页

摘要: reduction in inference time and peak memory usage | Sparse Neural Networks are increasing in |  increasing and as the Edge Computing and Fog paradigms are |  resolution images that are memory-friendly and suitable for |  Edge Computing. It is important to note that, as
关键词: Sparse artificial neural networks |  Binary classification |  Edge computing |  Medical datasets

4. Distributed Population-Based Simultaneous Perturbation Stochastic Approximation for Fine-Tuning Large Language Models NSTL国家科技图书文献中心

Yajing Tan |  Yuwei Huang... -  《PRICAI 2024,Part III》 -  Pacific Rim International Conference on Artificial Intelligence - 2025, - 21~26 - 共6页

摘要: of SPSA in the modern distributed computing |  in a relatively small-scale distributed computing | Very recently, a memory-efficient version |  memory of a single GPU, which often hinders the direct |  distributed computing resources, owing to their relatively
关键词: Population-based evolution |  Simultaneous perturbation stochastic approximation |  Fine-Tuning of large language models

5. Inference method for power large-scale model operation based on distributed computing resource scheduling NSTL国家科技图书文献中心

Xiaoguang Huang |  Yu Qin... -  《International Conference on Physics,Photonics,and Optical Engineering (ICPPOE 2024),Part One of Two Parts》 -  International Conference on Physics,Photonics,and Optical Engineering - 2025, - 135520V.1~135520V.10 - 共10页

摘要: distributed computing resources. In order to improve the |  parameters of computing power resources in different | Electric power computing resources are |  distributed in the respective regions of provincial data | , and the scheduling efficiency of computing resources
关键词: Distributed computing power resources |  Resource scheduling |  Large-scale power models |  Model inference

6. Reducing Memory Footprint in Deep Network Training by Gradient Space Reutilization NSTL国家科技图书文献中心

Yiming Dong |  Zhouchen Lin -  《Pattern Recognition and Computer Vision,Part II》 -  Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 376~390 - 共15页

摘要:, aiming at reducing memory usage in deep network |  computational and memory demands for training state-of-the-art |  cost associated with training. Memory-intensive |  accessible. In response to this challenge, we introduce a |  training by repurposing the memory allocated for
关键词: Deep learning optimization |  Efficient deep learning |  Memory footprint

7. Faster Leader Election and Its Applications for Mobile Agents with Parameter Advice NSTL国家科技图书文献中心

Ajay D. Kshemkalyani |  Manish Kumar... -  《Distributed Computing and Internet Technology》 -  International Conference on Distributed Computing and Internet Technology - 2025, - 108~123 - 共16页

摘要: studied problem in distributed computing. This paper |  minimize both time and memory usage. We study the leader |  election problem in a synchronous setting where each |  others, allowing us to measure time complexity in terms |  deterministically in O(n log~2 n + DΔ log n) rounds with each
关键词: Distributed algorithms |  Mobile agents |  Local communication |  Leader election |  MST |  MIS |  Gathering |  Minimal dominating set |  Time and memory complexity |  Graph parameters

8. Performance Characterisation of the 64-Core SG2042 RISC-V CPU for HPC NSTL国家科技图书文献中心

Nick Brown |  Maurice Jamieson -  《High Performance Computing》 -  ISC High Performance Conference - 2025, - 354~367 - 共14页

摘要: in embedded computing, it is yet to gain |  significant traction in High Performance Computing (HPC |  beneficial in future supercomputers especially as the |  in summer 2023, and at the time of writing now |  is a realistic proposition for HPC applications. In
关键词: RISC-V |  Sophon SG2042 |  NAS parallel benchmark suite (NPB) |  High performance computing (HPC)

9. DynGNN: Dynamic Memory-Enhanced Generative GNNs for Predicting Temporal Brain Connectivity NSTL国家科技图书文献中心

Scarlet Xiao |  Islem Rekik -  《Predictive Intelligence in Medicine》 -  International Conference on Medical Image Computing and Computer Assisted Intervention |  International Workshop on Predictive Intelligence in Medicine - 2025, - 111~123 - 共13页

摘要: connectomes with the actual memory capacity observed in the | ., memory capacity). All existing GNN models are cognition | -agnostic. In this paper, we aim to address this gap in |  computing paradigm, alongside our novel loss function |  which matches the memory capacity of the predicted
关键词: Temporal graph neural network |  Reservoir computing |  Memory capacity |  Time-dependent graph evolution prediction

10. UnsafeCop: Towards Memory Safety for Real-World Unsafe Rust Code with Practical Bounded Model Checking NSTL国家科技图书文献中心

Minghua Wang |  Jingling Xue... -  《Formal Methods,Part II》 -  International Symposium on Formal Methods - 2025, - 307~324 - 共18页

摘要: enhances BMC for analyzing memory safety in real-world |  memory-safety features and minimal runtime overhead |  developers to bypass safety guarantees, posing memory |  used to detect memory-safety problems, but it has |  bugs within a bounded number of executions. In this
关键词: Unsafe rust |  Memory safety |  Bounded model checking
检索条件In-memory computing

NSTL主题词

  • NSTL学科导航