检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Distributed cooperative guidance for multi-missile system with time-varying delays and switching topologies

Distributed cooperative guidance for multi-missile system wi...

引用

第三十九届中国控制会议

作者： Siquan Zhou Jie Ren Yong Heng Xiwang Dong Qingdong Li School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing Aerospace System Engineering Research Institute Beijing Institute of Electronic System Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Distributed cooperative guidance problems for multi-missile system with time-varying delays and switching topologies are investigated. Firstly, considering the complex communication environment, a two-step cooperative guidance strategy is proposed to achieve the simultaneous attack under time-varying delays and switching topologies. In the first step, a distributed cooperative guidance law using neighboring information is designed to coordinate range-to-go and leading angle based on feedback linearization and consensus theory. The second step starts while multi missiles disconnect from each other and hit the target using PNG（Proportional Navigation Guidance）. Then, the algorithm with three steps is presented to select the parameters in the cooperative guidance law. And the stability of the multi-missile system is proven using Lyapunov-Krasovskii theory. Finally, a numerical simulation is given to demonstrate the effectiveness of the proposed cooperative guidance strategy.

关键词： Cooperative guidance Distributed strategy Consensus theory Time-varying delays Switching topologies

来源：评论

学校读者我要写书评

暂无评论

Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities

arXiv

引用

arXiv 2024年

作者： Cui, Qimei You, Xiaohu Ni, Wei Nan, Guoshun Zhang, Xuefei Zhang, Jianhua Lyu, Xinchen Ai, Ming Tao, Xiaofeng Feng, Zhiyong Zhang, Ping Wu, Qingqing Tao, Meixia Huang, Yongming Huang, Chongwen Liu, Guangyi Peng, Chenghui Pan, Zhiwen Sun, Tao Niyato, Dusit Chen, Tao Khan, Muhammad Khurram Jamalipour, Abbas Guizani, Mohsen Yuen, Chau National Engineering Research Center of Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Department of Broadband Communication Peng Cheng Laboratory Shenzhen518055 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Fudan University Shanghai200433 China School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China CICT Mobile Communication Technology Co. Ltd. Beijing100020 China Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Jiao Tong University Shanghai200240 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310058 China China Mobile Research Institute Beijing100053 China Huawei Technologies Shanghai201206 China College of Computing and Data Science Nanyang Technological University Singapore117583 Singapore VTT Technical Research Centre of Finland Ltd. EspooFI-02044 VTT Finland Center of Excellence in Information Assurance King Saud University Riyadh11362 Saudi Arabia School of Electrical and Information Engineering University of Sydney NSW2006 Australia Abu Dhabi United Arab Emirates School of Electrical and Electronics Engineering Nanyang Technological University Singapore639798 Singapore

With the growing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and sixth-generation (6G) communication networks has emerged as a transformative paradigm. By embedding AI capabilities across various network layers, this integration enables optimized resource allocation, improved efficiency, and enhanced system robust performance, particularly in intricate and dynamic environments. This paper presents a comprehensive overview of AI and communication for 6G networks, with a focus on emphasizing their foundational principles, inherent challenges, and future research opportunities. We first review the integration of AI and communications in the context of 6G, exploring the driving factors behind incorporating AI into wireless communications, as well as the vision for the convergence of AI and 6G. The discourse then transitions to a detailed exposition of the envisioned integration of AI within 6G networks, delineated across three progressive developmental stages. The first stage, AI for Network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences. The second stage, Network for AI, highlights the role of the network in facilitating and buttressing AI operations and presents key enabling technologies, such as digital twins for AI and semantic communication. The final stage, AI as a Service, it is anticipated that future 6G networks will innately provide AI functions as services, supporting application scenarios like immersive communication and intelligent industrial robots. Specifically, we have defined the quality of AI service, which refers to a framework for measuring AI services within the network. We further summarize the standardization process of AI for wireless networks, highlighting key milestones and ongoing efforts. In addition, we conduct an in-depth analysis of the critical challenges faced by the integration of AI and communications

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Distributed State Estimation for Heterogeneous Mobile Sensor Networks with Varying Nodes

Distributed State Estimation for Heterogeneous Mobile Sensor...

引用

第三十九届中国控制会议

作者： Yingrong Yu Jie Ren Xiwang Dong Qingdong Li Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beihang University Beijing Aerospace System Engineering Research Institute Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

On background of cooperative air combat, state estimation of aerial maneuvering target with multi-sensor cooperative reconnaissance is discussed in this paper. Multiple moving platforms equipped with different kinds of detectors construct heterogeneous mobile sensor networks. Graph theory is adopted to describe the communication topology of the networks. In consideration of detection range limit, the number of sensors participating in the detection changes over time. An interactive multiple model algorithm（IMM） is utilized for target motion modeling. The local observation information is processed by Cubature Information Filter（CIF）. A weighted average consensus-based state estimation method for heterogeneous mobile sensor networks with varying nodes is put forward to fuse information from different sensors and obtain a consistent and precise tracking result. Moreover, the stability analysis of proposed method is provided detailed. Finally, numerical simulation results are given to illustrate the effectiveness of the theoretical results.

关键词： Cubature Information Filter consensus theory distributed state estimation mobile sensor networks stochastic boundedness

来源：评论

学校读者我要写书评

暂无评论

MDPL-net: Multi-layer Dictionary Learning Network with Added Skip Dense Connections

MDPL-net: Multi-layer Dictionary Learning Network with Added...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Yulin Sun Zheng Zhang Yang Wang Lin Wu Meng Wang School of Computer Science and Technology Soochow University Suzhou China Ministry of Education Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei China Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Dictionary learning (DL) is powerful for representation learning, while it fails to capture the deep hierarchical information hidden in data. In this paper, we propose a new generalized end-to-end mulita-layer representation learning architecture referred to as Multi-layer Dictionary Pair Learning Network (MDPL-net) for the deep sparse and hierarchical representation of images. To enable MDPL-net to conduct accurate classification, MDPL-net clearly integrates the skip connection end-to-end network and multi-layer deep sparse dictionary learning into a unified architecture. The representation learning module has several hidden DL blocks, where each hidden DL block has a dictionary pair learning (DPL) layer, a batch-norm layer and an activation function layer, and the DL blocks are connected in a feed-forward manner. To further improve the information flow and maintain the privileged features between different DL blocks, a novel skip dense connectivity pattern is deployed between hidden DL blocks, which can obtain more stable and discriminative features. The DPL layer jointly formulates the discriminative synthesis dictionary and analysis dictionary by minimizing reconstruction error within each batch over the feature maps from front layers. Extensive results on benchmark databases demonstrate the effectiveness of MDPL-net for discriminative representation and robust image classification.

关键词： Dictionaries databases Conferences Machine learning data mining Image reconstruction Image classification

来源：评论

学校读者我要写书评

暂无评论

Differentially private federated knowledge graphs embedding

arXiv

引用

arXiv 2021年

作者： Peng, Hao Li, Haoran Song, Yangqiu Zheng, Vincent Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Computer Science and Engineering HKUST Hong Kong AI Group Webank Co. Ltd School of Cyber Science and Technology Beihang University Beijing100191 China Peng Cheng Laboratory Shenzhen518066 China SKLSDE Beihang University Beijing100191 China

Knowledge graph embedding plays an important role in knowledge representation, reasoning, and data mining applications. However, for multiple cross-domain knowledge graphs, state-of-the-art embedding models cannot make full use of the data from different knowledge domains while preserving the privacy of exchanged data. In addition, the centralized embedding model may not scale to the extensive real-world knowledge graphs. Therefore, we propose a novel decentralized scalable learning framework, Federated Knowledge Graphs Embedding (FKGE), where embeddings from different knowledge graphs can be learnt in an asynchronous and peer-to-peer manner while being privacy-preserving. FKGE exploits adversarial generation between pairs of knowledge graphs to translate identical entities and relations of different domains into near embedding spaces. In order to protect the privacy of the training data, FKGE further implements a privacy-preserving neural network structure to guarantee no raw data leakage. We conduct extensive experiments to evaluate FKGE on 11 knowledge graphs, demonstrating a significant and consistent improvement in model quality with at most 17.85% and 7.90% increases in performance on triple classification and link prediction tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

CALPA-NET: Channel-pruning-assisted deep residual network for steganalysis of digital images

arXiv

引用

arXiv 2019年

作者： Tan, Shunquan Wu, Weilong Shao, Zilong Li, Qiushi Li, Bin Huang, Jiwu College of Computer Science and Software Engineering Shenzhen University College of Electronic and Information Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 518060 China

Over the past few years, detection performance improvements of deep-learning based steganalyzers have been usually achieved through structure expansion. However, excessive expanded structure results in huge computational cost, storage overheads, and consequently difficulty in training and deployment. In this paper we propose CALPA-NET, a ChAnneL-Pruning-Assisted deep residual network architecture search approach to shrink the network structure of existing vast, over-parameterized deep-learning based steganalyzers. By providing theoretical rationale, we demonstrate that the broad inverted-pyramid structure of existing deep-learning based steganalyzers contradicts the well-established model diversity oriented philosophy and is not suitable for steganalysis. Then a hybrid criterion combined with two network pruning schemes is introduced to adaptively shrink every involved convolutional layer in a data-driven manner. The resulting network architecture presents a slender bottleneck-like structure. We have conducted extensive experiments on BOSSBase+BOWS2 dataset and even a large-scale subset extracted from ImageNet CLS-LOC dataset. The experimental results show that the model structure generated by our proposed CALPA-NET can achieve comparative detection performance with less than two percent of parameters and about one third FLOPs compared to the original steganalytic model. The new model possesses even better adaptivity, transferability, and scalability. Copyright © 2019, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Non-structured Pruning for Deep-learning based Steganalytic Frameworks

Non-structured Pruning for Deep-learning based Steganalytic ...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Qiushi Li Zilong Shao Shunquan Tan Jishen Zeng Bin Li Shenzhen Key Laboratory of Media Security Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

ISBN: (数字)9781728132488

ISBN: (纸本)9781728132495

Image steganalysis aims to discriminate innocent cover images and those suspected stego images embedded with secret message. Recently, increasing advanced deep neural networks have been proposed and used in image steganalysis. Though those deep learning models can gain superior performance, they also result in redundancy of computational resource and memory storage. In this paper, we apply a non-structured pruning method to prune XuNet2 and SRNet - the two state-of-the-art deep-learning framework in the field of JPEG image steganalysis. We obtain the priorities of the connections among neurons according to a certain criterion, then keep those significant weights and prune those nonsignificant ones in the meantime. We have conducted extensive experiments on BOSSBase and BOWS image dataset. The experimental results demonstrate that our proposed non-structured pruning method can significantly reduce the cost of computation and storage required by the original deep-learning frameworks without affecting their detection accuracy.

关键词： Transform coding Training Convolution Computer architecture Computational modeling Brain modeling Testing

来源：评论

学校读者我要写书评

暂无评论

PHD: A Deep Learning Based Human Detection Framework for Panoramic Videos

PHD: A Deep Learning Based Human Detection Framework for Pan...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Jinting Tang Zhenhui Chen Yongkai Huo Peichang Zhang National Engineering Laboratory for Big Data System Computing Technology Research Institute for Future Media Computing School of Computer Science and Software Engineering Shenzhen University Shenzhen China The College of Information Engineering Shenzhen University Shenzhen China

Panoramic video has attracted substantial research attention as the coming video format. It is capable of providing 360 degree immersive experience of omnidirectional visual information. State-of-the-art detection networks may fail to detect humans on spherical images, which are normally represented in deformed rectangular shapes. In this paper, we propose a socalled Panoramic Human Detection (PHD) scheme to address the task of human detection in panoramic videos. Moreover, the PHD method is designed to detect humans by extracting multiple overlapping sub-images from each integral spherical image, where three-dimensional rotation of spherical images is employed to ensure consistency of sub-images. Two detection box filters are designed for removing redundant boxes. Our PHD method is capable of accomplishing the task of human detection in various panoramic video types. Experiments prove that our PHD method outperforms the baseline by 35% and 48.6% in terms of precision and recall, respectively.

关键词： Videos Task analysis Feature extraction Matrices Visualization Strain Transmission line matrix methods

来源：评论

学校读者我要写书评

暂无评论

Accuracy vs. Efficiency: Achieving both Through Hardware-Aware Quantization and Reconfigurable Architecture with Mixed Precision

Accuracy vs. Efficiency: Achieving both Through Hardware-Awa...

引用

IEEE International Conference on big data and Cloud computing (BdCloud)

作者： Libo Chang Shengbing Zhang Huimin Du Shiyu Wang Meikang Qiu Jihe Wang School of Computer Science Northwestern Polytechnical University and National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China School of Electronic Engineering Xi'an University of Posts and Telecommunication Xi'an China School of Computer Science Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Texas A&M University-Commerce Texas USA

We propose a hardware/software co-design framework, which leverages hardware-aware quantization and a reconfigurable processor to improve the computational efficiency of convolutional neural networks (CNNs) on tiny IoT devices based on reconfigurable platforms. Firstly, we proposed a multi-objective optimization value function that can weigh accuracy, the size of CNN models, and computational delay, to improve the efficiency of the mixed- precision quantization algorithm based on deep reinforcement learning. Secondly, we propose a reconfigurable CNN processor that can adapt to the computing characteristics of various quantized CNN models, as well as a reconfigurable computing array and an on-chip elastic buffer, to improve the performance and computing efficiency on edge equipment. Finally, we demonstrate the effectiveness of the proposed co-design method through an extensive evaluation of the Ultra96-V2 platform. With respect to the well-known CNNs—VGG-16, ResNet-50, and MobileNet-V2, the experimental result shows that the throughput of 216.6 GOPS, 214.0 GOPS, and 53.6 GOPS, the computing efficiency of 0.63GOPS/DSP, 0.64GOPS/DSP, and 0.24 GOPS/DSP, respectively. In addition, achieving a better optimized trade-off between the computing efficiency and accuracy compared with the recently proposed CNN processor with fixed bit-width and mixed-precision.

关键词： Adaptation models Quantization (signal) Computational modeling Reinforcement learning Throughput system-on-chip Reconfigurable architectures

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：