检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Miao, Zibo Pan, Yu Gao, Qing School of Mechanical Engineering and Automation Adaptive Robotics Harbin Institute of Technology Guangdong Key Laboratory of Intelligent Morphing Mechanisms Shenzhen518055 China The Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China The School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

ISBN: (纸本)9781665410205

In this paper we extend our previous research on coherent observer-based pole placement approach to study the synthesis of robust decoherence-free (DF) modes for linear quantum passive systems, which is aimed at preservation of quantum information. In particular, DF modes can be generated by placing the poles on the imaginary axis via a coherent feedback design scheme, and these modes can further be simultaneously made robust against perturbations to the system parameters by minimizing the condition number associated with imaginary poles. We develop explicit algebraic conditions for the existence of such a coherent quantum controller, with the corresponding deign procedure provided. Examples are given to illustrate the process of tuning the DF modes towards perfect robustness via the proposed pole placement technique. © 2024 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

DSSA: Dual-Side Sparse Systolic Array Architecture for Accelerating Convolutional Neural Network Training 22

DSSA: Dual-Side Sparse Systolic Array Architecture for Accel...

引用

Proceedings of the 51st International Conference on Parallel Processing

作者： Zhengbo Chen Qi Yu Fang Zheng Feng Guo Zuoning Chen Information Engineering University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Chinese Academy of Engineering China

ISBN: (纸本)9781450397339

Ever-growing CNN size incurs a significant amount of redundancy in model parameters, which in turn, puts considerable burden on hardware. Unstructured pruning is widely used to reduce model sparsity. While, the irregularity introduced by unstructured pruning makes it difficult to accelerate sparse CNNs on systolic array. To address this issue, a variety of accelerators have been proposed. SIGMA, the state-of-the-art sparse GEMM accelerator, achieves significant speedup over systolic array. However, SIGMA suffers from two disadvantages: 1) it only supports one-side sparsity, leaving potential for further performance gains; 2) SIGMA improves utilization of large-sized systolic arrays at the cost of extra overhead. In this paper, we propose DSSA, a dual-side sparse systolic array, to accelerate CNN training. DSSA bases its designs on a small-sized systolic array, which naturally achieves higher cell utilization without additional overhead. To facilitate dual-side sparsity processing, DSSA utilizes a cross-cycle reduction module to accumulate partial sum that belongs to the same column but being processed in different cycles. A comprehensive design space exploration is performed to seek the local optimal configurations for DSSA. We implement the logic design of DSSA using Verilog in RTL and evaluate its performance using a C++-based cycle-accurate performance simulator we built. Experimental results show that DSSA delivers, on average, a speedup of 2.13x and 13.81x over SIGMA and a basic systolic array with the same number of cells. Compared to SIGMA, DSSA incurs 16.59% area overhead and 25.49% power overhead when sparse filter is excluded, as SIGMA did.

关键词： Convolutional Neural Network Hardware Accelerator Sparsity Processing Systolic Array Unstructured Pruning

来源：评论

学校读者我要写书评

暂无评论

High-performance optimization of SM4-GCM based on FPGA

High-performance optimization of SM4-GCM based on FPGA

引用

advanced computing and Endogenous Security, International Conference on

作者： Shun Sen Lv Bin Li Xiaojie Chen Qinglei Zhou School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Mathmatical Engineering and Advanced Computing Zhengzhou China Schoo of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665424509

SM4-GCM is an encryption algorithm with authentication function. The algorithm achieves the purpose of data security and information integrity. The SM4-GCM algorithm, implemented using traditional software methods, has low throughput and high resource consumption. In order to further improve the algorithm performance, this paper uses FPGA to optimize the SM4-GCM algorithm to achieve full-pipeline parallel acceleration. Firstly, the SM4 module is optimized using pipelining techniques. Then, the GHASH module is optimized using the Karatsuba algorithm and fast reduction. Finally, a loosely coupled architecture is used to connect various modules with asynchronous FIFOs, which improves the resource utilization and throughput of the FPGA circuit. The experimental results show that the throughput of the optimized SM4-GCM algorithm reaches 28.8 Gbps. It is better than other schemes, has a higher throughput, and meets the actual application requirements.

关键词： Power demand Software algorithms Computer architecture Throughput Software Encryption Resource management

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Collaborative Aggregation Networks for Multi-Site Brain Disorder Diagnosis 4

Personalized Federated Learning with Collaborative Aggregati...

引用

4th International Conference on Industrial Automation, Robotics and Control engineering, IARCE 2024

作者： Si, Qian Li, Yang School of Cyber Science and Technology Beihang University Beijing China Department of Automation Science and Electrical Engineering The Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Beijing China Advanced Institute of Information Technology Peking University Beijing China Beihang University Beijing China

ISBN: (纸本)9798350380323

In multi-site brain disease diagnosis studies, traditional centralized training methods necessitate sharing medical data, posing significant privacy risks. Federated learning (FL) offers a privacy-preserving solution by enabling global model training through aggregating locally trained models from multiple data centers without sharing raw data. However, current FL approaches rely on a server-based network topology, where central server failure disrupts training. Additionally, data heterogeneity across sites often slows convergence and reduces accuracy. To overcome these issues, we introduce a decentralized personalized federated learning collaborative aggregation network (pFedCAN). This framework has two core components: (1) separating local models into shared and personalized layers, and (2) forming a collaborative aggregation network via similarity detection in the shared layers. Specifically, each center trains its local model, then separates it into shared and personalized layers. The shared layer is exchanged with other centers, while the personalized layer remains local. Data centers analyze similarities in received shared layers to build a collaborative network, where shared layers from similar centers are aggregated to refine the model. This approach flexibly adapts to varying levels of data heterogeneity, enhancing model training efficiency. Validation on public datasets, ABIDE I and ADHD, shows that the proposed method outperforms current leading techniques. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval 24

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficien...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zeng, Gangyan Zhang, Yuan Wei, Jin Yang, Dongbao Zhang, Peng Gao, Yiwen Qin, Xugong Zhou, Yu School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China Lenovo Research Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China TMCC College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9798400706868

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP's particular advantages in handling diverse forms of query text. The source code will be available at https://***/Gyann-z/FDP. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimal scheme for dynamic adjustment of active mirror in FAST system 2021

Optimal scheme for dynamic adjustment of active mirror in FA...

引用

2021 5th International Conference on Computer Science and Artificial Intelligence

作者： Hongchuan Zhou Jiaqi Liu Junyan Song Benchao Yang State Key Laboratory of Mathematical Engineering and advanced computing China

ISBN: (纸本)9781450384155

This paper mainly studies the optimal scheme of dynamic adjustment of active mirror in FAST system by establishing mathematical model. According to the constraints such as distance variation range, a mathematical model describing the dynamic trajectory of the position and angle of the active mirror is established, and the correctness of the solution of the model is verified by simulation. The optimal surface model is selected from all the results. When the measured object is directly above the fast system, it is modeled based on the ideal parabola to ensure that the expansion constraints and threshold conditions of the actuator are met. Because the distribution of actuator and cable in the whole fast system is not a uniform sphere, the change of radial distance of cable can be considered as the expansion of actuator; In addition, the model is optimized from two aspects: adjusting the position of focus on the horizontal plane and changing the size of zoom alignment. From these two aspects, the parabolic focusing range satisfying the expansion range is obtained. Finally, the optimization strategy of dynamic adjustment of active mirror in fast system is given.

关键词： Dimension reduction to simplify Mathematical modeling Optimization model

来源：评论

学校读者我要写书评

暂无评论

A Survey on Knowledge Graph Representation Learning with Text Information 21

A Survey on Knowledge Graph Representation Learning with Tex...

引用

Proceedings of the 3rd World Symposium on Software engineering

作者： Ling Wang Jicang Lu Gang Zhou State Key Laboratory of Mathematical Engineering and Advanced Computing China

ISBN: (纸本)9781450384094

Knowledge graph representation learning provides a lot of help for subsequent tasks such as knowledge graph completion, information retrieval, and intelligent question answering. By representing the knowledge graph as low-dimensional dense vectors, these tasks can improve efficiency significantly. However, limited by the sparseness and huge scale of the actual structure, representation learning only from a structural perspective can no longer meet the research *** improve the performance, researchers introduced auxiliary information into representation learning. This paper focuses on models using text as auxiliary information, dividing all text-combined models into two categories: Closed-world assumption models and Open-world assumption models. The former is limited by the model's demand for the structural representation of the graph itself, and can only predict the entities and relationships that already exist in the knowledge graph. The latter can handle entities that have not previously been seen during model training, and connect brand-new entities to the knowledge graph, which is more in line with the dynamic trend of the knowledge graph in real world. Open-world assumption models can be further subdivided into multiple types according different joint functions, such as alignment function, fusion function, score function and transformation function. This paper summarizes existing methods in detail and looks forward to future possible research directions.

关键词： Open-world assumption Representation learning Knowledge graph Text information

来源：评论

学校读者我要写书评

暂无评论

Open Set Recognition for Encrypted Traffic using Intra-class Partition and Boundary Sample Generation 5

Open Set Recognition for Encrypted Traffic using Intra-class...

引用

5th IEEE advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

作者： Li, Xue Fei, Jinlong Qi, Zan Lv, Zhuo Jiang, Heng PLA Information Engineering University State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China PLA Information Engineering University National Digital Switching System Engineering Technological Research Center Zhengzhou China

ISBN: (纸本)9781665479677

Existing deep learning-based encrypted traffic recognition methods can achieve high precision identification performance while protecting user privacy, but almost all of them focus on closed sets, in which training data and test data come from the same label space. However, the real network environment is open, and it is necessary for traffic identification systems to deal with previously unseen categories. To classify known categories at a fine granularity and identify unknown ones, we propose a novel open-set recognition method for encrypted traffic. The decision boundary sample generation method based on constrained Generative Adversarial Networks is presented to generate samples from low-density regions in the known data space. Furthermore, an end-to-end open-set classifier is built using the accurate and diverse simulative samples of unknown classes through intra-class partition and boundary sample generation. Finally, the effectiveness of the proposed method is validated through numerical experiments. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Software Vulnerability Mining Techniques Based on Data Fusion and Reverse engineering

引用

Wireless Communications and Mobile computing 2022年第0期2022卷

作者： Liu, Tieming State Key Laboratory of Mathematical Engineering and Advanced Computing Henan Zhengzhou450001 China

Software vulnerability mining is an important component of network attack and defense technology. To address the problems of high leakage rate and false positive rate of existing static analysis methods, this paper proposes a static analysis vulnerability detection technique based on data fusion for source code. By parsing the analysis results of different detection methods and fusing the data, the technique can effectively reduce the false positive rate and the false positive rate. A prototype of a scalable source code static analysis tool is designed and implemented, which can be automatically optimized by user feedback. Finally, an example is given to demonstrate how to uncover buffer overflow software vulnerabilities in the helpctr program based on reverse engineering techniques. The experimental results show that the false positive and false negative rates are significantly reduced compared to individual vulnerability detection methods. © 2022 Tieming Liu.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Attention-aligned mean-teacher learning for unsupervised domain adaptive person re-ID

引用

Science China Technological Sciences 2025年

作者： You LYU Zhen ZHANG Guoliang KANG Wei WEI Institute of Artificial Intelligence Beihang University Key Laboratory of Mathematics Informatics Behavioral Semantics Ministry of Education Beihang University State Key Laboratory of Software Development Environment and Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University School of Automation Science and Electrical Engineering Beihang University AVICAS Generic Technology Co. Ltd Zhongguancun Laboratory School of Mathematics Sciences Beihang University

In recent years, artificial intelligence has fueled the development of numerous applications [1, 2]. Person re-identification (re-ID) is a typical artificial intelligence system designed to automatically retrieve imag...

关键词：

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：