检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yiwei Li Jiaxin Liu Lin Yang Yating Zhang Kunlin Liu Ge Zhou Liangze Yin Wei Dong National University of Defense Technology Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recurrent neural networks (RNNs) are widely used in control system due to their dynamic capabilities. However, the control accuracy of RNN-based systems can be compromised by noise interference, and there has been little research on RNN-based control in disturbed multi-agent systems. To address this, we developed an enhanced distributed RNN (DRNN) structure and proposed a Novel DRNN-based Control Protocol (NDRNN-CP). This enhancement involves introducing a time-delay component, allowing the protocol to adaptively learn noise variation patterns. As a result, the NDRNN-CP effectively resists various periodic noise interferences and achieves more precise control of each agent. Additionally, our optimized activation function ensures that all agents reach consensus within a predefined time. To demonstrate the advantages of NDRNN-CP, we conducted extensive experiments that confirmed its significant improvements in noise signal resistance and convergence performance.

关键词： Resistance Protocols Recurrent neural networks Noise Resists Reliability Speech processing Multi-agent systems Convergence Resilience

来源：评论

学校读者我要写书评

暂无评论

distributed Graph neural network Inference With Just-In-Time Compilation For Industry-Scale Graphs

arXiv

引用

arXiv 2025年

作者： Wu, Xiabao Liu, Yongchao Qin, Wei Hong, Chuntao Ant Group China

Graph neural networks (GNNs) have delivered remarkable results in various fields. However, the rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference. Both computational complexity and memory usage have risen dramatically, with memory becoming a critical limitation. Although graph sampling-based subgraph learning methods can help mitigate computational and memory demands, they come with drawbacks such as information loss and high redundant computation among subgraphs. This paper introduces an innovative processing paradgim for distributed graph learning that abstracts GNNs with a new set of programming interfaces and leverages Just-In-Time (JIT) compilation technology to its full potential. This paradigm enables GNNs to highly exploit the computational resources of distributed clusters by eliminating the drawbacks of subgraph learning methods, leading to a more efficient inference process. Our experimental results demonstrate that on industry-scale graphs of up to 500 million nodes and 22.4 billion edges, our method can produce a performance boost of up to 27.4 times. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

distributed solar photovoltaic power prediction algorithm based on deep neural network

Journal of Engineering Research (Kuwait)

引用

Journal of Engineering Research (Kuwait) 2025年

作者： Zhao, Ming Li, Sitao Chen, Hao Ling, Min Chang, Hong Digital Platform Technology Company China Southern Power Grid Guangdong Shenzhen 518000 China

Solar photovoltaic (PV) power prediction is easily affected by weather factors. In order to reduce the solar photovoltaic (PV) power prediction deviation and improve the prediction accuracy, a distributed solar photovoltaic (PV) power prediction algorithm based on deep neural network is proposed. By deeply exploring the working principle of photovoltaic power generation, constructing a photovoltaic power generation system model, and systematically analyzing various factors that affect photovoltaic power generation, detailed classification of weather types can be achieved. On this basis, outlier detection, standardization processing, and normalization techniques are used to deeply clean and optimize the raw data, effectively avoiding the problem of neuron saturation. The use of wavelet packet decomposition method to decompose the photovoltaic power generation sequence into multiple sub sequences significantly reduces the difficulty of prediction. The effective fusion of LSTM (Long Short-Term Memory) and BPNN (Back Propagation neural network), and the fine adjustment of the fusion ratio parameter through genetic algorithm, ultimately achieved high-precision prediction of distributed photovoltaic power under complex and variable weather conditions. The experimental results show that the proposed method can accurately predict photovoltaic power under different weather conditions, and the prediction results are reliable. © 2024 The Authors

关键词： BPNN Deep neural network distributed photovoltaic Genetic algorithm LSTM Power prediction Weather factors

来源：评论

学校读者我要写书评

暂无评论

Reducing Feed-Forward neural network processing Time Utilizing Matrix Multiplication Algorithms on Heterogeneous distributed Systems

Reducing Feed-Forward Neural Network Processing Time Utilizi...

引用

International Conference on Computational Intelligence, Communication Systems and networks, CICSYN

作者： Ali Kattan Rosni Abdullah Rosalina Abdul Salam School of Computer Science Universiti Sains Islam Malaysia Penang Malaysia School of Computer Science Universiti Sains Malaysia Penang Malaysia

This paper presents a work in progress that aims to reduce the overall training and processing time of feed-forward multi-layer neural networks. If the network is large processing is expensive in terms of both; time and space. In this paper, we suggest a cost-effective and presumably a faster processing technique by utilizing a heterogeneous distributed system composed of a set of commodity computers connected by a local area network. neural network computations can be viewed as a set of matrix multiplication processes. These can be adapted to utilize the existing matrix multiplication algorithms tailored for such systems. With Java technology as an implementation means, we discuss the different factors that should be considered in order to achieve this goal highlighting some issues that might affect such a proposed implementation.

关键词： Feedforward systems neural networks Feedforward neural networks Artificial neural networks Hardware Computer networks Parallel processing distributed computing Computational modeling Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

PP-Stream: Toward High-Performance Privacy-Preserving neural network Inference via distributed Stream processing

PP-Stream: Toward High-Performance Privacy-Preserving Neural...

引用

International Conference on Data Engineering

作者： Qingxiu Liu Qun Huang Xiang Chen Sa Wang Wenhao Wang Shujie Han Patrick P. C. Lee Peking University The Chinese University of Hong Kong Zhejiang University Institute of Computing Technology Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Privacy preservation is critical for neural network inference, which often involves collaborative execution of different parties to make predictions on sensitive data based on sensitive neural network models. However, the expensive cryptographic operations of privacy preservation also pose performance chal-lenges to neural network inference. We address this performance-security tension by designing PP-Stream, a distributed stream processing system for high-performance privacy-preserving neural network inference. PP-Stream adopts hybrid privacy-preserving mechanisms for linear and non-linear operations of neural network inference. It treats inference data as real-time data streams, and parallelizes the inference operations across multiple pipelined stages that are executed by multiple servers and threads. It also solves the load-balanced resource allocation across servers and threads as an optimization problem. We prototype PP-Stream and show via testbed experiments that it achieves low inference latencies on various neural network models.

关键词： Privacy Tensors Instruction sets neural networks Prototypes Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

MDS-DOA: Fusing Model-Based and Data-Driven Approaches for Modular, distributed, and Scalable Direction-of-Arrival Estimation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年第2期72卷 941-952页

作者： Assoa, Adou Sangbone Bhat, Ashwin Ryu, Sigang Raychowdhury, Arijit Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Korea Aerosp Univ Dept Elect & Informat Engn Goyang Si 10540 Gyeonggi Do South Korea

Massive MIMO systems are promising for wireless communications beyond 5G, but scalable Direction-of-Arrival (DOA) estimation in these systems is challenging due to the increasing number of required antennas. Existing solutions, model-based or data-driven (typically using neural networks), face scalability issues with the growing antenna array size. To address this issue, we propose a hybrid system that makes the overall approach scalable. In the front-end, we employ a modular distributed approach namely, the method of sparse linear inverse to compute a proxy spectrum from the sampled covariance matrix of the antenna subarrays. The proxy drives a fixed lightweight back-end which consists of a 1-dimensional Convolution neural network (1D-CNN) and a simplified peak extraction. The input proxy dimension being independent of the antenna count makes the neural network input invariant of the array size, enabling it to handle multiple array sizes without requiring any modification of the neural network structure. To reduce the computation of the covariance matrix and proxy spectrum, we employ a system of subarrays with Nearest-Neighbor communication. The proposed approach was implemented on a Xilinx ZCU102 FPGA targeting 100 MHz frequency for 8 to 256-element arrays. We achieve below 1 ms processing time for an array of 256 antennas while requiring significantly less computation than both model-based and data-driven approaches for large antenna arrays.

关键词： Antenna arrays neural networks Array signal processing Covariance matrices Arrays Antennas Direction-of-arrival estimation Mathematical models Estimation Computational modeling Direction-of-arrival MIMO array signal processing distributed array system 5G 6G neural network

来源：评论

学校读者我要写书评

暂无评论

neural network based distributed query processing strategy selector

Mathematical Modelling and Scientific Computing

引用

Mathematical Modelling and Scientific Computing 1993年第SECTIOA期2卷 299-299页

作者： Perrizo, William Ram, Prabhu

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Scheduling on a Field-Programmable Gate Array Cluster Using Configurable Deep Learning Accelerators

引用

INFORMATION 2025年第4期16卷 298-298页

作者： Fang, Tianyang Perez-Vicente, Alejandro Johnson, Hans Saniie, Jafar Illinois Inst Technol Dept Elect & Comp Engn Chicago IL 60616 USA

This paper presents the development and evaluation of a distributed system employing low-latency embedded field-programmable gate arrays (FPGAs) to optimize scheduling for deep learning (DL) workloads and to configure multiple deep learning accelerator (DLA) architectures. Aimed at advancing FPGA applications in real-time edge computing, this study focuses on achieving optimal latency for a distributed computing system. A novel methodology was adopted, using configurable hardware to examine clusters of DLAs, varying in architecture and scheduling techniques. The system demonstrated its capability to parallel-process diverse neural network (NN) models, manage compute graphs in a pipelined sequence, and allocate computational resources efficiently to intensive NN layers. We examined five configurable DLAs-Versatile Tensor Accelerator (VTA), Nvidia DLA (NVDLA), Xilinx Deep processing Unit (DPU), Tensil Compute Unit (CU), and Pipelined Convolutional neural network (PipeCNN)-across two FPGA cluster types consisting of Zynq-7000 and Zynq UltraScale+ System-on-Chip (SoC) processors, respectively. Four deep neural network (DNN) workloads were tested: Scatter-Gather, AI Core Assignment, Pipeline Scheduling, and Fused Scheduling. These methods revealed an exponential decay in processing time up to 90% speedup, although deviations were noted depending on the workload and cluster configuration. This research substantiates FPGAs' utility in adaptable, efficient DL deployment, setting a precedent for future experimental configurations and performance benchmarks.

关键词： deep learning accelerator (DLA) deep neural network (DNN) distributed computing field-programmable gate array (FPGA) neural processing unit (NPU) system-on-chip (SoC)

来源：评论

学校读者我要写书评

暂无评论

distributed Approximating Functional Wavelet based neural network in ECG signal processing

Distributed Approximating Functional Wavelet based neural ne...

引用

IEEE International Conference on Automation, Quality and Testing, Robotics, AQTR

作者： Z. German-Sallo L. David Petru Maior University of Tg Mureş Romania

For ECG signal processing, information extraction from a noisy background is the fundamental objective. Filtering (noise suppression, baseline wander elimination) is a very important step in efficient ECG signal features extracting to enhance the performance of automatic detection and classification of different cardiac diseases. In this paper we used distributed approximating functional (DAF) wavelets to develop algorithms for signal approximation and filtering. These algorithms use moving average artificial neural network with wavelet type Hermite activating function. They are evaluated in MATLAB with signals from the MIT-BIH arrhythmia database and comparisons are made with the classical (radial basis function and sigmoid type activating function) artificial neuronal networks. New functions were created and integrated into MATLAB environment. The outcomes indicate a good performance tradeoff between accuracy and response time, making this type of algorithms desirable also for real-time implementation

关键词： neural networks Electrocardiography Signal processing Signal processing algorithms Data mining Filtering MATLAB Background noise Feature extraction Cardiac disease

来源：评论

学校读者我要写书评

暂无评论

A Survey on Parameter Server Architecture: Approaches for Optimizing distributed Centralized Learning

引用

IEEE ACCESS 2025年 13卷 30993-31015页

作者： Provatas, Nikodimos Konstantinou, Ioannis Koziris, Nectarios Natl Tech Univ Athens Sch Elect & Comp Engn Athens 11527 Greece Univ Thessaly Dept Informat & Telecommun Lamia 35100 Greece

Deep learning has emerged as a cornerstone technology across various domains, from image classification to natural language processing. However, the computational and data demands of training large-scale neural networks pose significant challenges. distributed learning approaches, particularly those leveraging data parallelism, have become critical to addressing these challenges. Among these, the parameter server architecture stands out as a widely adopted and scalable solution, enabling efficient training of large models across distributed systems. This survey provides a comprehensive exploration of the parameter server architecture, detailing its design principles and operation. It categorizes and critically analyzes research advancements across five key aspects: consistency control, network optimization, parameter management, straggler handling, and fault tolerance. By synthesizing insights from a wide range of studies, this work highlights the trade-offs and practical effectiveness of various approaches while identifying open challenges and future research directions. The survey aims to serve as a foundational resource for researchers and practitioners striving to enhance the performance and scalability of distributed deep learning systems.

关键词： Servers Training Data models Computational modeling Deep learning Surveys Parallel processing Training data Solid modeling neural networks distributed systems network parameter server synchronization centralized

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：