检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing 400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Speed Measurement Method of Rail Transit Based on Millimeter-Wave Radar 1

引用

5th International Symposium for Intelligent Transportation and Smart City, ITASC 2022

作者： Shen, Tuo Xie, Lanxin Luo, Jinnan Zeng, Xiaoqing Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety Shanghai201804 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Institute of Rail Transit Tongji University Shanghai China

ISBN: (数字)9789819922529

ISBN: (纸本)9789819922512

The growing use of millimeter-wave radars in the intelligent transportation field and increasing accuracy provide new possibilities for train speed measurement. This paper proposes a measuring train speed method by using millimeter-wave radar to detect static objects. The millimeter-wave radar was used to obtain and process objects data. Then, using the RANSAC algorithm to extract the static objects group, and calculated the relative speed of the millimeter-wave radar and the static objects group. Finally, we completed the comparative experiment of using millimeter-wave radar and odometer to measure train speed in a real track environment. The results show that the measurement error of this method is less than 1.5 m/s, and it has the characteristics of low cost, fast speed measurement, and high precision. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Natural Man–Machine Interaction Technology and Its Application for Lunar Robot 23rd

Multi-modal Natural Man–Machine Interaction Technology and ...

引用

23rd IFToMM China International Conference on Mechanism and Machine science and engineering, IFToMM CCMMS 2022

作者： Chen, Meng Zhang, Chongfeng Qin, Xiaofei Ma, Jia Zhang, Wenqi Shanghai Key Laboratory of Spacecraft Mechanism Shanghai201108 China Institute of Aerospace System Engineering Shanghai Shanghai201109 China Shanghai Academy of Spaceflight Technology Shanghai201109 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789811993978

For the requirements of multi-modal man–machine interaction between astronauts and robots in lunar surface exploration, research on three interaction modes and test system based on speech, body posture and tactile recognition are carried out. An improved speech feature classification and recognition algorithm based on Mel-scale Frequency Cepstral Coefficients (MFCC), a three-stage body posture recognition algorithm based on target detection—node recognition—skeleton action recognition, and a tactile recognition algorithm based on Radial Basis Function network (RBF) are proposed. In the body posture recognition algorithm, a lightweight CVC-Net model is developed based on the classical HourglassNet algorithm. Deep separable convolution, attention mechanism and improved up-sampling method are introduced. A lightweight network and adaptive graph convolution module for skeleton action recognition are designed by introducing the information of human body joints and skeleton vectors. Above algorithm is suitable for the embedded computing platform and can greatly reduce the number of module parameters while ensuring the detection accuracy. Based on the simulated lunar surface environment, lunar robot and simulated space suit, the ground test verification of three modes of command recognition is realized, which can meet the low power consumption, lightweight and real-time requirements of lunar robot for recognition algorithms and the embedded computing platform. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Balance Multi-Head Attention based on Software and Hardware Co-design 9

Balance Multi-Head Attention based on Software and Hardware ...

引用

9th IEEE International Conference on Cyber Security and Cloud Computing and 8th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2022

作者： Xu, Dian Hu, Wei Liu, Fang Fan, Zimeng Shi, Qingsong Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System College of Computer Science Wuhan China Wuhan University Department of Information Engineering Wuhan Institute of City School of Computer Science Wuhan China Zhejiang University College of Computer Science Hangzhou China

ISBN: (数字)9781665480666

ISBN: (纸本)9781665480666

Recently, the Transformer-based models have achieved leading results in many research areas such as natural language processing and computer vision. However, since Transformer-based models have a huge computational complexities, optimization for Transformer is the focus of current research. the core of Transformer models is the attention module, and in this paper we propose a software and hardware co-designed attention module, which reduces the computational units of the multi-head attention module by balancing the The inference time of the attention module is reduced by balancing the computational units of multiple attention modules. At the same time, we design the corresponding structure on FPGA, which accelerate 14.6x inference time in comparison with the original attention module implementation on GPU. We applied this attention module to multiple visual Transformer models and tested the accuracy difference between the balanced multi-head attention module-based model and the original model on CIFAR-10, and obtained a result of 80.46%, which lower from the original version by 0.18%. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation

Cross-Domain Few-Shot Relation Extraction via Representation...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhongju Yuan Zhenkun Wang Genghui Li School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the few labeled sentences embedding with the embeddings of the query sentences using a trained metric function. However, as these domains always have considerable differences from those in the training dataset, the generalization ability of these approaches on unseen relations in many domains is limited. Since the prototype is necessary for obtaining relationships between entities in the latent space, we suggest learning more interpretable and efficient prototypes from prior knowledge and the intrinsic semantics of relations to extract new relations in various domains more effectively. By exploring the relationships between relations using prior information, we effectively improve the prototype representation of relations. By using contrastive learning to make the classification margins between sentence embedding more distinct, the prototype's geometric interpretability is enhanced. Additionally, utilizing a transfer learning approach for the cross-domain problem allows the generation process of the prototype to account for the gap between other domains, making the prototype more robust and enabling the better extraction of associations across multiple domains. The experiment results on the benchmark FewRel dataset demonstrate the advantages of the suggested method over some state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Large-Scale Sorting with Optimized Bandwidth Utilization

引用

ACM Transactions on Reconfigurable Technology and systems 2025年第2期18卷 1-27页

作者： Mingqian Sun Guangwei Xie Fan Zhang Wei Guo Xitian Fan Li Chen Jiayu Du School of Cyber Science and Engineering Southeast University Nanjing China School of Computer Science Fudan University Shanghai China National Digital Switching System Engineering and Technological Research Center Zhengzhou China Hongzhen Information Technology Co. Ltd Shanghai China Purple Mountain Laboratories Nanjing China

Fast sorting of large-scale data is an essential task for data centers. In previous works, the existing computational model of sorting kernel still results in lower bandwidth utilization on the external memory bus. And the execution of merge operations in merge sort circuit on FPGAs depends on control commands from the host CPU. In this case, the merge sort circuit is not fully offloaded to hardware layer for acceleration, resulting in a performance loss. We design an on-chip merge sort controller to efficiently command the merge sort process. The proposed controller has the ability to schedule multiple on-chip computing kernels simultaneously in a more efficient mode, thus ensuring that the circuit has a better bandwidth utilization. Meanwhile, fundamental factors affecting the performance of merge sort are studied and analyzed, and we propose a high-performance merge sort architecture. Results show that using the proposed controller-centered architecture, an overall improvement of 20%–30% in sorting throughput can be achieved. Compared with the state-of-the-art previous merge sorting implementation on FPGA, our circuit can achieve 1.22/1.46\(\times\) speedup.

关键词： Merge sort FPGA system architecture on-chip controller

来源：评论

学校读者我要写书评

暂无评论

Enabling Real World Scale Structural Superlubricity All-Atom Simulation on the Next-Generation Sunway Supercomputer 23

Enabling Real World Scale Structural Superlubricity All-Atom...

引用

2023 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2023

作者： Duan, Xiaohui Wang, Jin Gao, Ping Ma, Ming Gan, Lin Liu, Xin Fu, Haohuan Xue, Wei Chen, Dexun Yang, Guangwen Liu, Weiguo School of Software Shandong University China International School for Advanced Studies Trieste Italy Tsinghua University Department of Computer Science and Technology Beijing China Department of Engineering Mechanics Center for Nano and Micro Mechanics Tsinghua University Beijing China National Supercomputing Center in Wuxi Wuxi China Ministry of Education Key Lab for Earth System Modeling Department of Earth System Science Tsinghua University Beijing China

ISBN: (纸本)9798400701092

Molecular dynamics (MD) simulation can provide an affordable way for inspecting microscopic phenomena, which is a powerful complement to real-world experiments. But the spatial scale of MD simulations is usually magnitudes smaller than experiment systems. In this paper, we present our work, redesigning the widely used inter-layer potential in structural superlubricity. By carrying out a specialized neighbor list for inter-layer potential computation, the total memory access amount is reduced significantly. Besides, a simple but efficient vectorization strategy is implemented based on the new neighbor list. In the extreme case, our work can scale to 38 million cores to achieve a sustainable performance of 61 PFLOPS, enabling a simulation of a superlubricity system of 32 μm2 with 7.2 billion atoms at 4.75 ns/day, which is 11,834 times of reported largest scale simulation in superlubricity systems in contact area and almost ten times faster in time-to-solution. Furthermore, we have done a simulation at 9 μm2 which results in consistency with real-world experiments and verified some theoretical predictions in the mesoscopic scale. © 2023 ACM.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

An end-to-end instance segmentation method based on improved ConvNeXt V2

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 384-392页

作者： Wang, Wenlu Sun, Ying Xu, Manman Bai, Dongxu Huang, Li Zou, Chunlong Chen, Baojia Tang, Dalai Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance China Three Gorges University Hubei Yichang China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot China

In order to improve the efficiency of indoor mobile robots in locating and segmenting environmental instances, an instance segmentation method based on RTMDet is proposed. Firstly, the more powerful ConvNeXt V2 is used as the backbone network of the model, which improves the performance of the existing RTMDet model. Subsequently, NAS-FPN is used as a converged network to detect the network at any given time. Finally, AdamW is used as the model optimiser, which effectively solves the problem of excessive memory occupation when updating parameters and improves the performance of the model. The proposed method obtains the highest evaluation index in all cases. After training and testing on the Cityscapes data set, the recognition accuracy reaches 65.0%. © 2024 Inderscience Enterprises Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Transfer Task-Averaged Natural Gradient for Efficient Many-Task Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Li, Yanchi Gong, Wenyin Gu, Qiong China University of Geosciences School of Computer Wuhan430074 China Hubei University of Arts and Science School of Computer Engineering Xiangyang441053 China Hubei University of Arts and Science Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Xiangyang441053 China

With the increasing requirement for computational efficiency in evolutionary algorithms when tackling many optimization tasks concurrently, many-task optimization (MaTO) has gained much attention in recent years. It involves extracting and transferring the knowledge from successful search experiences across many tasks. As the number of tasks and variable scale grows in MaTO, the need for efficient knowledge transfer in evolutionary algorithms becomes indispensable. In this paper, we present a task-averaged natural gradient-assisted natural evolution strategy (TNG-NES) to deal with MaTO efficiently. The task-averaged natural gradient captures how a group of task distributions evolves, considering their overall trends of mean and covariance. This can accelerate the optimization process across all tasks by leveraging the evolutionary similarities among multiple task search distributions. Notably, TNG-NES exhibits linear computational complexity concerning the number of tasks for knowledge transfer. Additionally, to adaptively utilize task-averaged natural gradient for distribution evolution and mitigate negative transfer, we introduce a transfer adaptive control mechanism for TNG-NES. We conducted extensive experiments on CEC19-MaTO, WCCI22-MaTO, our proposed large-scale MaTO benchmark suite, and real-world applications. The results validate the effectiveness of TNG-NES, outperforming state-of-the-art MaTO algorithms. © 1997-2012 IEEE.

关键词： Knowledge transfer

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：