检索结果-内蒙古大学图书馆

A user model based on mobile environment

Ruan Jian Xue Bao/Journal of software 2011年第SUPPL. 2期22卷 120-128页

作者： Du, Yi Tian, Feng Dai, Guo-Zhong Wang, Feng Wang, Hong-An Intelligence Engineering Laboratory Institute of Software Chinese Academy of Sciences Beijing 100190 China School of Information Science and Engineering Graduate University Chinese Academy of Sciences Beijing 100190 China Yunnan Provincial Key Laboratory of Computer Application Kunming University of Science and Technology Kunming 650500 China

It's very important to help developers design user interface for application in an intelligent user interface. Nowadays, the number of mobile based applications increases greatly, but there are no proper user model to guide the design and development of user interface. This article takes different types of functions and parameters in consideration, and proposes a user model and user modeling method based on activity theory. In addition, this article describes the improved VSM algorithm in detail. Finally, an application and an informal experiment are designed to prove the efficiency of given user model. This work can be used to guide the design and development of mobile user interface under mobile environment. ©2011 Journal of software.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

DPA-2:a large atomic model as a multitask learner

引用

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

来源：评论

学校读者我要写书评

暂无评论

Self-Ensembling GAN for Cross-Domain Semantic Segmentation

arXiv

引用

arXiv 2021年

作者： Xu, Yonghao He, Fengxiang Du, Bo Tao, Dacheng Zhang, Liangpei The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Vienna1030 Austria JD Explore Academy *** Inc. Beijing100176 China School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430079 China

Deep neural networks (DNNs) have greatly contributed to the performance gains in semantic segmentation. Nevertheless, training DNNs generally requires large amounts of pixel-level labeled data, which is expensive and time-consuming to collect in practice. To mitigate the annotation burden, this paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model, the latter of which is a common barrier shared by most adversarial training-based methods. We theoretically analyze SE-GAN and provide an O(1/√N) generalization bound (N is the training sample size), which suggests controlling the discriminator's hypothesis complexity to enhance the generalizability. Accordingly, we choose a simple network as the discriminator. Extensive and systematic experiments in two standard settings demonstrate that the proposed method significantly outperforms current state-of-the-art approaches. The source code of our model is available online (https://***/YonghaoXu/SE-GAN). Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

The spirit of evolutionary algorithms

引用

Journal of Computing and Information Technology 1999年第1期7卷 1-18页

作者： Michalewicz, Zbigniew Esquivel, Susana Gallarti, Raul Michalewicz, Maciej Tao, Guo Trojanowski, Krzysztof Department of Computer Science University of North Carolina CharlotteNC28223 United States Departamento de Informatica Facuitad de Cs. Fisico-Matematicas y Naturales Universidad Naclonal de San Luis Ejercito de los Andes 950 local 106 San Luis5700 Argentina Institute of Computer Science Polish Academy of Sciences ul. Ordona 21 Warsaw01-237 Poland State Key Laboratory of Software Engineering Wuhan University WuhanHubei430072 China

Evolutionary algorithms (EAs), which are based on a powerful principle of evolution: survival of the fittest, and which model some natural phenomena: genetic inheritance and Darwinian strife for survival, constitute an interesting category of modern heuristic search. During the last two decades there has been a growing interest in these algorithms;today, many complex software systems include at least some evolutionary component. However, the process of building an evolutionary program is still art rather than science;often it is based on the intuition and experience of the designer. In this introductory article we present some important ideas behind the construction of evolutionary algorithms. These ideas are illustrated by three test cases: the transportation problem, a particular nonlinear parameter optimization problem, and the traveling salesman problem. We conclude the paper with a brief discussion on how an evolutionary algorithm can be tuned to the problem while solving it, which may increase further efficiency of the algorithm in a significant way.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network

arXiv

引用

arXiv 2023年

作者： Li, Tianyu Zou, Shufan Chang, Xinghua Zhang, Laiping Deng, Xiaogang School of Computer Science Sichuan University Chengdu610065 China College of Aerospace Science and Engineering National University of Defense Technology Changsha410000 China Unmanned Systems Research Center National Innovation Institute of Defense Technology Beijing100071 China Academy of Military Sciences Beijing100190 China Tianfu Engineering-oriented Numerical Simulation & Software Innovation Center Sichuan University Chengdu610207 China

The rapid development of deep learning has significant implications for the advancement of Computational Fluid Dynamics (CFD). Currently, most pixel-grid-based deep learning methods for flow field prediction exhibit significantly reduced accuracy in predicting boundary layer flows and poor adaptability to geometric shapes. Although Graph Neural Network (GNN) models for unstructured grids based unsteady flow prediction have better geometric adaptability, these models suffer from error accumulation in long-term predictions of unsteady flows. More importantly, fully data-driven models often require extensive training time, greatly limiting the rapid update and iteration speed of deep learning models when facing more complex unsteady flows. Therefore, this paper aims to balance the demands for training overhead and prediction accuracy by integrating physical constraints based on the finite volume method into the loss function of the graph neural network. Additionally, it incorporates a twice-massage aggregation mechanism inspired by the extended stencil method to enhance the unsteady flow prediction accuracy and geometric shape generalization ability of the graph neural network model on unstructured grids. We focus particularly on the model's predictive accuracy within the boundary layer. Compared to fully data-driven methods, our model achieves better predictive accuracy and geometric shape generalization ability in a shorter training time. Copyright © 2023, The Authors. All rights reserved.

关键词： Unsteady flow

来源：评论

学校读者我要写书评

暂无评论

Novel technique based on triangle decimation for tetrahedral simplification

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2007年第12期35卷 2343-2346页

作者： Wang, Xuan-Ming Wu, Ju-Ying Wu, En-Hua State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing 100080 China Graduate School Chinese Academy of Sciences Beijing 100080 China Air Force Engineering University Xi'an 710077 China

How to simplify a large scale tetrahedral dataset in order to use in the real time rendering is of more importance. A novel technique based on triangle decimation for tetrahedral simplification is described here. A triangle area ratio is defined as cost function for every triangular in the model. Through this ratio, a list of priority sequences is obtained in the per-compute period. The triangle which of high priority will be deleted firstly. Compared to the published paper, this method can be used to delete at least 8 tetrahedral in one triangle decimation cycle. In the test model, we can delete at most 13 tetrahedral one time. The results of this technique are of high practical use especially in the real time compression transformation of tetrahedral, finite element computation and rendering.

关键词： Data processing

来源：评论

学校读者我要写书评

暂无评论

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

FedMDC: Enabling Communication-Efficient Federated Learning over Packet Lossy Networks via Multiple Description Coding

FedMDC: Enabling Communication-Efficient Federated Learning ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Federated learning (FL) generally suffers significant communication overhead from high-traffic gradient synchronization. The majority of existing studies on this problem aim at compressing gradients under the premise of reliable transmission. While transmission reliability can be ensured via TCP by default, the notably increased latency and retransmitted packets are prohibitive for most clients in FL. To tackle this issue, we propose FedMDC, a retransmission-free compression framework for FL over packet lossy networks. Given clients’ limited resources, FedMDC adopts multiple description coding to encode gradients into redundant descriptions for erasure resilience simply through multiplying an overcomplete matrix; and then quantizes these descriptions for compression. To further reduce quantization distortion and computational overhead, a reduced decoding algorithm is developed by decoding the aggregation of all clients’ encodings in conjunction with a customized dither quantization design. Besides, FedMDC explicitly supports adaptive bitrates subject to clients’ heterogeneous communication budgets, which maximize resource utilization to facilitate distortion reduction and accelerate model convergence. Theoretical analysis and experimental results both demonstrate the effectiveness of our scheme.

关键词： Quantization (signal) Federated learning Distortion Propagation losses Encoding Decoding Reliability Synchronization Resource management Resilience

来源：评论

学校读者我要写书评

暂无评论

FedTC: Enabling Communication-Efficient Federated Learning via Transform Coding

FedTC: Enabling Communication-Efficient Federated Learning v...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Jianwei Niu Tao Ren State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Federated learning (FL) enables distributed training via periodically synchronizing model updates among participants. Communication overhead becomes a dominant constraint of FL since participating clients usually suffer from limited bandwidth. To tackle this issue, top-k based gradient compression techniques are broadly explored in FL context, manifesting powerful capabilities in reducing gradient volumes via picking significant entries. However, previous studies are primarily conducted on the raw gradients where massive spatial redundancies exist and positions of non-zero (top-k) entries vary greatly between gradients, which both impede the achievement of deeper compressions. Top-k may also degrade the performance of trained models due to biased gradient estimations. Targeting the above issues, we propose FedTC, a novel transform coding based compression framework. FedTC transforms gradients into a new domain with more compact energy distributions, which facilitates reducing spatial redundancies and biases in subsequent sparsification. Furthermore, non-zero entries across clients from different rounds become highly aligned in the transform domain, motivating us to partition the gradients into smaller entry blocks with various alignment levels to better exploit these alignments. Lastly, positions and values of non-zero entries are independently compressed in a block-wise manner with our customized designs, through which a higher compression ratio is achieved. Theoretical analysis and extensive experiments consistently demonstrate the effectiveness of our approach.

关键词： Training Quantization (signal) Costs Federated learning Redundancy Transform coding Estimation

来源：评论

学校读者我要写书评

暂无评论

M3OFF: Module-Compositional Model-Free Computation Offloading in Multi-Environment MEC

M3OFF: Module-Compositional Model-Free Computation Offloadin...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Tao Ren Zheyuan Hu Jianwei Niu Weikun Feng Hang He State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Computation offloading is one of the key issues in mobile edge computing (MEC) that alleviates the tension between user equipment's limited capabilities and mobile application's high requirements. To achieve model-free computation offloading when reliable MEC dynamics are unavailable, deep reinforcement learning (DRL) has become a popular methodology. However, most existing DRL-based offloading approaches are developed for a single MEC environment, with invariant system bandwidth, edge capability, task types, etc., while realistic MEC scenarios tend to be of high diversity. Unfortunately, in multi-MEC environments, DRL-based offloading faces at least two challenges, learning inefficiency and interference of offloading experiences. To address the challenges, we propose a DRL-based Multi-environmental Module-compositional Modelfree computation OFFloading (M 3 OFF) framework. M 3 OFF generates offloading policies using module composition instead of a single DRL network so that learning efficiency could be improved by reusing the same modules and learning interference could be reduced by composing different modules. Furthermore, we design multiple module composition-specific training methods for M 3 OFF, including alternate modules-and-composer updates to improve training stability, loss-regularization to avoid module degeneration, and module-dropout to mitigate overfitting. Extensive experimental results on both simulation and testbed demonstrate that M 3 OFF outperforms the performances of most state-of-the-arts in multi-MEC and reaches close to single-MEC.

关键词： Training Visualization Multi-access edge computing Computational modeling Interference Bandwidth Stability analysis

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：