检索结果-内蒙古大学图书馆

Towards optimized tensor code generation for deep learning on sunway many-core processor

Frontiers of Computer Science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

A survey on federated learning:a perspective from multi-party computation

引用

Frontiers of Computer Science 2024年第1期18卷 93-103页

作者： Fengxia LIU Zhiming ZHENG Yexuan SHI Yongxin TONG Yi ZHANG Institute of Artificial Intelligence and Key Laboratory of Mathematics Informatics Behavioral Semantics Beihang UniversityBeijing 100191China State Key Laboratory of Software Development Environment and Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang UniversityBeijing 100191China Pengcheng Laboratory Shenzhen 518055China Zhongguancun Laboratory Beijing 100190China Institute for Mathematical Sciences and Engineering Research Center of Financial Computing and Digital Engineering Renmin University of ChinaBeijing 100872China

Federated learning is a promising learning paradigm that allows collaborative training of models across multiple data owners without sharing their raw *** enhance privacy in federated learning,multi-party computation can be leveraged for secure communication and computation during model *** survey provides a comprehensive review on how to integrate mainstream multi-party computation techniques into diverse federated learning setups for guaranteed privacy,as well as the corresponding optimization techniques to improve model accuracy and training *** also pinpoint future directions to deploy federated learning to a wider range of applications.

关键词： sfederated learning multi-party ycomputation privacy-preserving data mining distributed learning

来源：评论

学校读者我要写书评

暂无评论

Shipping Label Generation based on VGG19 Network 2

Shipping Label Generation based on VGG19 Network

引用

2nd International Conference on advanced Manufacturing Technology and Manufacturing systems, ICAMTMS 2023

作者： Wang, Haifeng Wu, Tong Yang, Kun Xiong, Yong Center for Advanced Metering Infrastructure National Institute of Metrology Beijing China Intelligent System Research and Development Laboratory Wayzim Technology Co. Ltd Wuxi China

ISBN: (纸本)9781510667327

Shipping labels are an important component of logistics. It includes all the vital information to have packages successfully delivered. During the packaging and delivery processes, the shipping labels can be damaged, which poses a challenge to the effectiveness of the sorting machine. In this paper, a shipping label generation model based on VGG19 network is proposed. Our model first splits the images into shipping labels and then extracts the features of unreadable ones, finally different types of shipping labels applied such features are generated. To evaluate the performance of our model, we conduct experiments on the sorting machine using the generated 7,500 labels by the model. The results show that the generated labels can evaluate the sorting machine effectively, which demonstrates the encouraging performance of our model. © 2023 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Computer-Vision-Based Non-Contact Paste Concentration Measurement*

Computer-Vision-Based Non-Contact Paste Concentration Measur...

引用

2024 International Conference on Automation in Manufacturing, Transportation and Logistics, ICaMaL 2024

作者： Liang, Tailin Yuan, Zhaolin School of Computer Science and Engineering Beihang University State Key Laboratory of Software Development Environment Beijing China Research Institute of Advanced Manufacturing Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hong Kong Hong Kong

ISBN: (纸本)9798350378658

For monitoring the paste concentration, existing techniques, such as ultrasonic concentration meters and neutron meters, suffer from radiation hazards and low precision in high concentrations. This paper proposes a novel non-contact concentration measurement method based on deep learning. With the dataset collected by preparing the paste with different concentrations and taking photographs from the paste surface, a convolutional neural network is trained to extract the features from images and predict the concentration. The experiments indicate that the measurement accuracy is close to 88.79 % for the manual stirring paste dataset and 91.42 % for the automatic stirring paste dataset, which are sufficient in industrial applications. As a substitution of traditional concentration measurement instruments, the proposed vision-based concentration measurement method is non-contact and its accuracy is sufficient in industrial applications. © 2024 IEEE.

关键词： Radiation hazards

来源：评论

学校读者我要写书评

暂无评论

Collective Behavior Regulation in Drone Swarms via Pinning Strategies 7th

Collective Behavior Regulation in Drone Swarms via Pinning...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Liu, Gaoxiang Liu, Kexin Chen, Lei School of Automation Science and Electrical Engineering Beihang University Beijing100191 China The State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789819733354

In this paper, we discuss the collective behavior of drone swarms and remark that the swarm behavior can be realized by pinning a few nodes. Additionally, the selection of pinning nodes effects the global characteristic. Compared with other methods, the uniform degree selection of pinning nodes in a swarm exhibits better performance. In order to verify the effectiveness of our pinning strategy, we conduct simulations in a self-driven drone swarm, in which the experimental results confirm the availability of our conclusion. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Single‑Neuron Reconstruction of the Macaque Primary Motor Cortex Reveals the Diversity of Neuronal Morphology

引用

Neuroscience Bulletin 2025年第3期41卷 525-530页

作者： Siyu Li Yan Shen Yefei Chen Zexuan Hong Lewei Zhang Lufeng Ding Chao‑Yu Yang Xiaoyang Qi Quqing Shen Yanyang Xiao Pak‑Ming Lau Zhonghua Lu Fang Xu Guo‑Qiang Bi CAS Key Laboratory of Brain Function and Disease Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230026China Interdisciplinary Center for Brain Information Shenzhen-Hong Kong Institute of Brain ScienceShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Shenzhen Technological Research Center for Primate Translational Medicine Shenzhen Key Laboratory for Molecular Biology of Neural DevelopmentShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China The Key Laboratory of Biomedical Imaging Science and System Chinese Academy of SciencesShenzhen 518055China CAS Key Laboratory of Brain Connectome and Manipulation the Brain Cognition and Brain Disease InstituteShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Faculty of Life and Health Sciences Shenzhen University of Advanced TechnologyShenzhen 518107China

Dear Editor,The primary motor cortex,also known as MOp in rodents,F1,or M1 in primates[1],plays a crucial role in autonomous motor *** is interconnected with other motor control structures such as the basal ganglia,thalamus,and *** these connections,the corticostriatal system plays a significant role in functions including action selection,motor control,sequence learning,and habit formation[2].

关键词： habit formation autonomous motor controlit morphology action selectionmotor corticostriatal system neuron basal gangliathalamusand primary motor cortexalso

来源：评论

学校读者我要写书评

暂无评论

Simultaneous enhancement of sensitivity, resonant frequency, and overload capability of piezoresistive accelerometers by heavily-doped fillet structures on sensing beams

引用

IEEE Sensors Journal 2025年第11期25卷 19138-19146页

作者： Xia, Yong Wang, Tao Lv, Yang Han, Xiangguang Yu, Mingzhi Tan, Renjie Huang, Mimi Jia, Chen Zhao, Libo Sun, Lin Yang, Ping Lu, Dejiang Xi'an Jiaotong University School of Mechanical Engineering State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an710049 China Ningbo CRRC Times Transducer Technology Co. LTD Department of Basic Research and Development Ningbo315021 China Research Institute for Intelligent Sensing Technology and System School of Instrument Science and Technology State Key Laboratory for Manufacturing Systems Engineering State Industry-Education Integration Center for Medical Innovations International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an Jiaotong University Xi'an710049 China Shandong Laboratory of Advanced Materials and green Manufacturing at Yantai Yantai264000 China

High sensitivity, high natural frequency, and high overload capability are desired for accelerometers used in industrial applications, but simultaneously enhancing all is challenging. Here, via designing novel heavily-doped fillet structures, we prove the sensitivity, resonant frequency, and overload capability can be simultaneously enhanced. The enhancements are attributed to regulations of stress concentration and effective sensing regions by the heavily-doped fillets. The sensors with and without fillets are designed, fabricated, packaged, and tested. The results show a sensitivity of 0.31±0.02 mV/g@5V, a natural frequency of 37.87±2.09 kHz, and an overload of 10040.17±531.76 g for sensors with 10-μm fillets, which are superior to 0.27±0.01 mV/g@5V, 34.13±0.90 kHz, and 7368.55±843.92 g for those no-fillet counterparts. Additionally, the developed sensor further exhibited feasibility in air-bearing vibration monitoring. The proposed design is envisioned to give insights into the novel designs of high-performance stress-based sensors, including accelerometers, pressure sensors, and strain gauges. © 2001-2012 IEEE.

关键词： Strain gages

来源：评论

学校读者我要写书评

暂无评论

MAKT: Multichannel Attention Networks based Knowledge Tracing with Representation Learning 11

MAKT: Multichannel Attention Networks based Knowledge Tracin...

引用

11th IEEE International Conference on Teaching, Assessment and Learning for Engineering, TALE 2022

作者： Jiang, Xuyang Ouyang, Yuanxin Liu, Zhuang Rong, Wenge Xiong, Zhang Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beijing China

ISBN: (纸本)9781665491174

As an effective and emerging component of intelligent education, Knowledge Tracing(KT) achieves the combination of artificial intelligence and individualized learning, whose aim is to assess students' mastery of knowledge concepts and assist in developing learning plans. Several existing KT models either use concepts sequence as input and evaluate students' knowledge state or treat exercise as input to predict students' future performance. In this paper, we introduce a constraint factor to extract concepts' and exercises' relation matrix, design three methods in representation learning, and propose a Multichannel Attention Networks based KT model(MAKT). Specifically, we restrict the co-occurrence relationship within a time window to extract the relation matrix and then train their representations via graph generative learning, graph contrastive learning, and matrix decomposition, respectively. In MAKT, a sliding window is implemented by multichannel where input sequence is sequentially lagged in turn by one position and attention mechanism is applied. We conduct experiments on several benchmark datasets and demonstrate that MAKT with concepts' and exercises' representation trained by matrix decomposition outperforms state-of-the-art models. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Explainable Recommendation over Knowledge Graphs with Negative Sampling 19

Reinforcement Learning-Based Explainable Recommendation over...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhang, Siyuan Ouyang, Yuanxin Liu, Zhuang Rong, Wenge Xiong, Zhang Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University Engineering Research Center of Advanced Computer Application Technology Ministry of Education Beijing China

ISBN: (纸本)9798350346558

Introducing knowledge graphs (KGs) into the recommender systems not only improves their performance but also enhances the interpretability. However, most KG-based recommendation methods have the problem of inefficiency and ex-post explanation, which reinforcement learning (RL) methods can solve properly. Most existing RL-based methods for explainable recommendations only consider positive rewards when designing the reward part of the RL environment, which is defective and misleads the policy of the RL agent. To address this problem, we propose Reinforced Knowledge Graph Reasoning with Reinforced Negative Sampling (RKGR-RNS) by introducing a negative sampling method into RL-based recommendation, which refines the reward mechanism to help optimize the agent's policy. And a judge module is proposed to improve the performance of the recommender system further. Experiments on three real datasets demonstrate that our method is better than the state-of-the-art baseline. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

UAV navigation in high dynamic environments:A deep reinforcement learning approach

引用

Chinese Journal of Aeronautics 2021年第2期34卷 479-489页

作者： Tong GUO Nan JIANG Biyue LI Xi ZHU Ya WANG Wenbo DU School of Electronic and Information Engineering Beihang UniversityBejing 100083China Key Laboratory of Advanced Technology of Near Space Information System(Beihang University) Ministry of Industry and Information Technology of ChinaBeijing 100083China Research Institute of Frontier Science Beihang UniversityBeijing 100083China College of Software Beihang UniversityBeijing 100083China State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100083China

Unmanned Aerial Vehicle(UAV) navigation is aimed at guiding a UAV to the desired destinations along a collision-free and efficient path without human interventions, and it plays a crucial role in autonomous missions in harsh environments. The recently emerging Deep Reinforcement Learning(DRL) methods have shown promise for addressing the UAV navigation problem,but most of these methods cannot converge due to the massive amounts of interactive data when a UAV is navigating in high dynamic environments, where there are numerous obstacles moving *** this work, we propose an improved DRL-based method to tackle these fundamental *** be specific, we develop a distributed DRL framework to decompose the UAV navigation task into two simpler sub-tasks, each of which is solved through the designed Long Short-Term Memory(LSTM) based DRL network by using only part of the interactive data. Furthermore, a clipped DRL loss function is proposed to closely stack the two sub-solutions into one integral for the UAV navigation problem. Extensive simulation results are provided to corroborate the superiority of the proposed method in terms of the convergence and effectiveness compared with those of the state-of-the-art DRL methods.

关键词： Autonomous vehicles Deep learning Motion planning Navigation Reinforcement learning Unmanned Aerial Vehicle(UAV)

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：