检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Detection Method for Shilling Attacks Based on Features of Automatic Extraction

引用

China Communications 2019年第8期16卷 130-146页

作者： Yaojun Hao Fuzhi Zhang Jinbo Chao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China Department of Computer Science and Technology Xinzhou Teachers UniversityXinzhou 034000China

Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.

关键词： shilling attack ensemble detection features of automatic extraction marginalized linear denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Submodularity-based False Data Injection Attack Scheme in Multi-agent Dynamical systems

arXiv

引用

arXiv 2022年

作者： Luo, Xiaoyu Zhao, Chengcheng Fang, Chongrong He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The State Key Laboratory of Industrial Control Technology Institute of Cyberspace Research Zhejiang University China The Department of Electrical and Computer Engineering University of Victoria BC Canada

Consensus in multi-agent dynamical systems is prone to be sabotaged by the adversary, which has attracted much attention due to its key role in broad applications. In this paper, we study a new false data injection (FDI) attack design problem, where the adversary with limited capability aims to select a subset of agents and manipulate their local multi-dimensional states to maximize the consensus convergence error. We first formulate the FDI attack design problem as a combinatorial optimization problem and prove it is NP-hard. Then, based on the submodularity optimization theory, we show the convergence error is a submodular function of the set of the compromised agents, which satisfies the property of diminishing marginal returns. In other words, the benefit of adding an extra agent to the compromised set decreases as that set becomes larger. With this property, we exploit the greedy scheme to find the optimal compromised agent set that can produce the maximum convergence error when adding one extra agent to that set each time. Thus, the FDI attack set selection algorithms are developed to obtain the near-optimal subset of the compromised agents. Furthermore, we derive the analytical suboptimality bounds and the worst-case running time under the proposed algorithms. Extensive simulation results are conducted to show the effectiveness of the proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of three properties of mobile interactive systems based on variable Petri nets

arXiv

引用

arXiv 2021年

作者： Yang, Ru Ding, Zhijun Jiang, Changjun Zhou, MengChu The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University The Department of Computer Science and Technology Tongji University Shanghai201804 China The Institute of Systems Engineering Macau University of Science and Technology 999078 China The Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

Due to the mobility and frequent disconnections, the correctness of mobile interaction systems, such as mobile robot systems and mobile payment systems, are often difficult to analyze. This paper introduces three critical properties of systems, called system connectivity, interaction soundness and data validity, and presents a related modeling and analysis method, based on a kind of Petri nets called VPN. For a given system, a model including component nets and interaction structure nets is constructed by using VPNs. The component net describes the internal process of each component, while the interaction structure net reflects the dynamic interaction between components. Based on this model, three properties are defined and analyzed. The case study of a practical mobile payment system shows the effectiveness of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Regenerative Particle Thompson Sampling

arXiv

引用

arXiv 2022年

作者： Zhou, Zeyu Hajek, Bruce Choi, Nakjung Walid, Anwar Department of Radiology Mayo Clinic RochesterMN United States Department of Electrical and Computer Engineering The Coordinated Science Laboratory University of Illinois at Urbana-Champaign United States Network System and Security Research Nokia Bell Labs Murray HillNJ United States Amazon New York United States

This paper proposes regenerative particle Thompson sampling (RPTS), a flexible variation of Thompson sampling. Thompson sampling itself is a Bayesian heuristic for solving stochastic bandit problems, but it is hard to implement in practice due to the intractability of maintaining a continuous posterior distribution. Particle Thompson sampling (PTS) is an approximation of Thompson sampling obtained by simply replacing the continuous distribution by a discrete distribution supported at a set of weighted static particles. We observe that in PTS, the weights of all but a few fit particles converge to zero. RPTS is based on the heuristic: delete the decaying unfit particles and regenerate new particles in the vicinity of fit surviving particles. Empirical evidence shows uniform improvement from PTS to RPTS and flexibility and efficacy of RPTS across a set of representative bandit problems, including an application to 5G network slicing. © 2022, CC BY-SA.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Improved Human Detection Algorithm by Indoor W-Band FMCW RADAR using K-means Technique

Improved Human Detection Algorithm by Indoor W-Band FMCW RAD...

引用

International Electrical engineering Congress (iEECON)

作者： Aman Worasutr Denchai Worasawate Tiwat Pongthavornkamol Kazuhiko Fukawa Faculty of Engineering Kasetsart University Bangkok Thailand Location and Automatic Identification System Research Team National Electronic and Computer Technology Center Pathum Thani Thailand Tokyo Institute of Technology Tokyo Japan

ISBN: (纸本)9781728195841;9781728195858

This paper proposes the improved indoor human detection algorithm from data provided by W-Band FMCW radar by using k-mean technique. The data provided by the radar contain both humans and nun-human objects. To identify non-human objects, the obtained data are filtered by the velocity and RCS of the detected objects. The K-means algorithm is applied to the filtered dataset to estimate the positions of humans. The estimated positions of humans are much closed to the actual ones.

关键词： Electrical engineering Radar cross-sections Radar detection Human factors Filtering algorithms Millimeter wave radar Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Stability and sensitivity analysis of multi-vendor, multi-terminal HVDC systems

arXiv

引用

arXiv 2021年

作者： Liao, Yicheng Wu, Heng Wang, Xiongfei Ndreko, Mario Dimitrovski, Robert Winter, Wilhelm School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden AAU Energy Aalborg University Aalborg Denmark Electrical System Design TenneT TSO GmbH Bayreuth Germany

The stability of multi-vendor, multi-terminal HVDC systems can be analyzed in frequency domain by black-box impedance models using the generalized Nyquist stability criterion. Based on the impedance stability analysis, a multi-level sensitivity analysis approach using frequency-domain sensitivity functions is proposed to identify the root cause of potential instability. Case studies on a four-terminal HVDC system are carried out for stability and sensitivity analysis based on the impedance measurement in PSCAD. The analysis results are finally validated by electromagnetic transient simulations. Copyright © 2021, The Authors. All rights reserved.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

ScalaBFS: A scalable BFS accelerator on HBM-enhanced FPGAs

arXiv

引用

arXiv 2021年

作者： Li, Kexin Liu, Chenhao Shao, Zhiyuan Wang, Zeke Wu, Minkang Chen, Jiajie Liao, Xiaofei Jin, Hai 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 Wuhan30074 China Collaborative Innovation Center of Artificial Intelligence Zhejiang University China

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalaBFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalaBFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalaBFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalaBFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalaBFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280). Copyright © 2021, The Authors. All rights reserved.

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

Design and Implementation of DSP Cache

Design and Implementation of DSP Cache

引用

International Conference on Communication Technology (ICCT)

作者： Kunkun Liang Jun Wu Haoqi Ren Zhifeng Zhang Bin Tan Electronics and Information Engineering College Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science Fudan University Shanghai China College of Electronics and Information Engineering Jinggangshan University Ji'an China

ISBN: (纸本)9781665432078

The cache can improve the DSP processor's access speed to external memory and solve the “Storage Wall” problem. Designing an efficient and flexible cache module plays an vital role in improving the memory access efficiency and overall performance of the DSP. Based on the analysis of DSP storage level design requirements, combined with the actual pipeline structure of the DSP processor SWIFT independently developed by our laboratory, in this paper, we design and implement first- level instruction and data cache. For L1 D-Cache, the relevant conflict detection and processing module is designed to support four parallel Load/Store access requests. The size of the cache can be flexibly configured according to actual application requirements to achieve a balance between power consumption and latency. To write back the modified data left in the cache before the cache size is changed, the Cacheclean instruction is designed. Finally, module-level functional verification and logic synthesis are carried out. The results show that the cache function meets expectations, and the critical path after logic synthesis optimization meets the requirement of 1GHz frenuency.

关键词： Frequency synthesizers Power demand Instruction sets Conferences Pipelines Memory management Process control

来源：评论

学校读者我要写书评

暂无评论

Generation of super-resolved optical needle and multifocal array using graphene oxide metalenses

引用

Opto-Electronic Advances 2021年第2期4卷 1-11页

作者： Hongtao Wang Chenglong Hao Han Lin Yongtian Wang Tian Lan Chengwei Qiu Baohua Jia Centre for Translational Atomaterials Faculty of ScienceEngineering and TechnologySwinburne University of TechnologyP.O.Box 218Hawthorn VIC 3122Australia Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of ChinaSchool of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117583Singapore Engineering Product Development Pillar Singapore University of Technology and Design8 Somapah Road487372Singapore

Ultrathin flat metalenses have emerged as promising alternatives to conventional diffractive lenses,offering new possibilities for myriads of miniaturization and interfacial ***-based materials can achieve both phase and amplitude modulations simultaneously at a single position due to the modification of the complex refractive index and thickness by laser conversion from graphene oxide into graphene like *** this work,we develop graphene oxide metalenses to precisely control phase and amplitude modulations and to achieve a holistic and systematic lens design based on a graphene-based material *** experimentally validate our strategies via demonstrations of two graphene oxide metalenses:one with an ultra-long(~16λ)optical needle,and the other with axial multifocal spots,at the wavelength of 632.8 nm with a 200 nm thin *** proposed graphene oxide metalenses unfold unprecedented opportunities for accurately designing graphene-based ultrathin integratable devices for broad applications.

关键词： femtosecond laser reduction graphene oxide metalens multifocal spots optical needle

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：