检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiang, Feihu Qin, Chuan Yao, Kaichun Fang, Chuyu Zhuang, Fuzhen Zhu, Hengshu Xiong, Hui University of Science and Technology of China China Career Science Lab BOSS Zhipin Beijing China PBC School of Finance Tsinghua University Beijing China Institute of Software Chinese Academy of Sciences China Institute of Artificial Intelligence Beihang University China Zhongguancun Laboratory China The Thrust of Artificial Intelligence The Hong Kong University of Science and Technology Guangzhou China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Guangzhou HKUST Fok Ying Tung Research Institute China

Efficient knowledge management plays a pivotal role in augmenting both the operational efficiency and the innovative capacity of businesses and organizations. By indexing knowledge through vectorization, a variety of knowledge retrieval methods have emerged, significantly enhancing the efficacy of knowledge management systems. Recently, the rapid advancements in generative natural language processing technologies paved the way for generating precise and coherent answers after retrieving relevant documents tailored to user queries. However, for enterprise knowledge bases, assembling extensive training data from scratch for knowledge retrieval and generation is a formidable challenge due to the privacy and security policies of private data, frequently entailing substantial costs. To address the challenge above, in this paper, we propose EKRG, a novel Retrieval-Generation framework based on large language models (LLMs), expertly designed to enable question-answering for Enterprise Knowledge bases with limited annotation costs . Specifically, for the retrieval process, we first introduce an instruction-tuning method using an LLM to generate sufficient document-question pairs for training a knowledge retriever. This method, through carefully designed instructions, efficiently generates diverse questions for enterprise knowledge bases, encompassing both fact-oriented and solution-oriented knowledge. Additionally, we develop a relevance-aware teacher-student learning strategy to further enhance the efficiency of the training process. For the generation process, we propose a novel chain of thought (CoT) based fine-tuning method to empower the LLM-based generator to adeptly respond to user questions using retrieved documents. Finally, extensive experiments on real-world datasets have demonstrated the effectiveness of our proposed framework. © 2024, CC BY.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Cloud computing in electric vehicles charging control and dispatch optimization

Cloud computing in electric vehicles charging control and di...

引用

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Dan Wu Bo Liu Zhijian Chen Wenyan Xie Xiang Huang Shuwei Pei Bin Sheng Donghan Feng Information Center China Southern Power Grid Co. Ltd. Dept. of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Network & Information Branch Guangdong Electric Power Design Institute Guangzhou China Chinese Academy of Sciences Institute of Software Beijing China Dept. of Electrical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781479920327

Charging of large-scale electric vehicles will have a significant impact on the grid so that their charging schedule needs to be optimized. The traditional centralized scheduling method requires high performance in information exchange and computing. Based on the analysis of the features of electric vehicle charging load and the research of cloud computing, we propose a cloud computing based schedule platform for optimal charging of electric vehicles. In addition, the function and implementation of the three basic modules of the platform (the data collection module, the cloud computing center and the control center) are exposed. The platform performs well in optimal scheduling for electric vehicles. In addition, the platform can also make full use of the computing resource and reduce the communication congestion.

关键词： Electric vehicles Cloud computing Optimal scheduling Power grids

来源：评论

学校读者我要写书评

暂无评论

Revisiting Token Dropping Strategy in Efficient BERT Pretraining

arXiv

引用

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Liu, Xuebo Zhang, Min Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China Institute of Computing and Intelligence Harbin Institute of Technology China University of Sydney Australia

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training time without degrading much performance on downstream tasks. However, we empirically find that token dropping is prone to a semantic loss problem and falls short in handling semantic-intense tasks (§2). Motivated by this, we propose a simple yet effective semantic-consistent learning method (SCTD) to improve the token dropping. SCTD aims to encourage the model to learn how to preserve the semantic information in the representation space. Extensive experiments on 12 tasks show that, with the help of our SCTD, token dropping can achieve consistent and significant performance gains across all task types and model sizes. More encouragingly, SCTD saves up to 57% of pretraining time and brings up to +1.56% average improvement over the vanilla token dropping. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Provably secure Certificate based ring signature without pairing

引用

International Journal of Network Security 2014年第4期16卷 278-285页

作者： Qin, Zhiguang Xiong, Hu Li, Fagen School of Computer Science and Engineering University of Electronic Science and Technology of China No. 4 North Jianshe Road Chenghua District chengdu Sichuan 610054 China Key Lab of Network Security and Cryptology Fujian Normal University No. 8 Shangsan Road Cangshan District Fuzhou Fujian 350007 China State Key Laboratory of Information Security Institute of Software Chinese Academy of Sciences No. 19 Yuquan Road Shijingshan District Beijing 100190 China

In Eurocrypt 2003, Gentry introduced the notion of certificate-based encryption. The merit of certificate-based encryption lies in implicit certificate and no private key escrow. This feature is desirable especially for the efficiency and the real spontaneity of ring signature, which involve a large number of public keys in each execution. In this paper, we propose an efficient certificate-based ring signature scheme which does not require any pairing computation. Furthermore, this scheme is proven secure under the Discrete Logarithm assumption in the random oracle model. To the best of authors' knowledge, this is the first construction of certificate-based ring signature scheme in the literature that has such kind of feature.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Research on the transformer model in computer vision

引用

AIP Conference Proceedings 2024年第1期3194卷

作者： Kaipeng Li Yizhen Song College of Computer Science and Software Engineering Shenzhen University Shenzhen China Reading Academy Nanjing University of Information Science & Technology Nanjing China

In the realm of computer vision, the visual Transformer model is commonly utilized as researchers have improved the Transformer model. The purpose of this paper is to study the transformer model in the field of computer vision, to summarise the visual transformer model, and to introduce the applications in the field of computer vision. This paper firstly introduces the idea and structure of the transformer model, including the Self-Attention Mechanism, Multi-Head Attention and secondly gives an overview of the research progress of Transformer model the second is a review of the research progress of the Transformer model, including the Vision Transformer, Swin Transformer and other improved models, selecting representative models and their applications to be introduced, laying a foundation for the subsequent research work. As the field of computer vision continues to evolve, the Transformer model needs to be further developed to handle different types of data and tasks to meet the needs of increasingly complex applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Framework for Unsupervised Anomaly Detection over Edge-Assisted Internet of Things

引用

ACM Transactions on Sensor Networks 1000年

作者： Yumeng Liu Hongan Wang Xu Zheng Ling Tian Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China School of Computer Science and Engineering University of Electronic Science and Technology of China China

The detection of anomaly status plays a pivotal role in the maintenance of public transportation and facilities in smart cities. Owing to the pervasively deployed sensing devices, one can collect and apply multi-dimensional sensing data to detect and analyze potential anomalies and react promptly. Current efforts concentrate on offline manners and fail to fit the situation in smart cities, where efficient and online solutions are expected. In this paper, a novel framework is designed for anomaly detection over edge-assisted Internet-of-Things (IoTs). The framework allows periodical data collection from sensors and continuous anomaly detection at the edge node. A novel efficient and unsupervised deep learning model is designed to balance the resource consumption and accuracy for anomaly detection, based on the combination of a convolutional autoencoder and adversarial training. Meanwhile, the proposed framework also adopts an adaptive strategy for continuous anomaly detection to reduce the overall resource consumption. According to theoretical analysis and evaluation on several real-world datasets, the proposed framework can discover the potential correlation features among multi-dimensional sensing data, and efficiently detect the abnormality of public transportation and facilities in smart cities.

关键词： Anomaly detection Smart city Internet of Thing Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Entertainment for Education. Digital Techniques and Systems 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Xiaopeng Zhang Shaochun Zhong Zhigeng Pan Kevin Wong Ruwei Yun

ISBN: (数字)9783642145339

ISBN: (纸本)9783642145322

With the technical advancement of digital media and the medium of communication in recent years, there is a widespread interest in digital entertainment. An emerging te- nical research area edutainment, or educational entertainment, has been accepted as education using digital entertainment. Edutainment has been recognized as an eff- tive way of learning using modern digital media tools, like computers, games, mobile phones, televisions, or other virtual reality applications, which emphasizes the use of entertainment with application to the education domain. The Edutainment conference series was established in 2006 and subsequently - ganized as a special event for researchers working in this new interest area of e-learning and digital entertainment. The main purpose of Edutainment conferences is to facilitate the discussion, presentation, and information exchange of the scientific and technological development in the new community. The Edutainment conference series becomes a valuable opportunity for researchers, engineers, and graduate s- dents to communicate at these international annual events. The conference series - cludes plenary invited talks, workshops, tutorials, paper presentation tracks, and panel discussions. The Edutainment conference series was initiated in Hangzhou, China in 2006. Following the success of the first event, the second (Edutainment 2007 in Hong Kong, China), third (Edutainment 2008 in Nanjing, China), and fourth editions (Edutainment 2009 in Banff, Canada) were organized. Edutainment 2010 was held during August 16–18, 2010 in Changchun, China. Two workshops were jointly org- ized together with Edutainment 2010.

关键词： computers and Education

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Control in Finite Time Stabilization for Synchronization of Chaotic Systems

引用

International Scholarly Research Notices 2013年第1期2013卷

作者： Zhan-Shan Zhao Jing Zhang Lian-Kun Sun School of Computer Science and Software Engineering Tianjin Polytechnic University Tianjin 300387 *** State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing 100190 *** Tianjin Vocational Institute Tianjin 300410 ***

An adaptive sliding mode control for chaotic systems synchronization is considered. The design of robust finite time convergent controller is based on geometric homogeneity and integral sliding mode manifold. The knowledge of the upper bound of the system uncertainties is not prior required. The chaos synchronization is presented to system stability based on the Lyapunov stability theory. The simulation results show the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Yuwei Zhang Zhi Jin Ying Xing Ge Li Fang Liu Jiaxin Zhu Wensheng Dou Jun Wei Key Laboratory of System Software (Chinese Academy of Sciences) Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer Science Peking University School of Computer Science Wuhan University China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications China School of Computer Science Peking University China State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Beihang University China

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a noticeable gap in existing approaches lies in the oversight of collaborative facets intrinsic to bug resolution, treating the process as a single-stage endeavor. Moreover, most approaches solely take the buggy code snippet as input for LLMs during the patch generation stage. To mitigate the aforementioned limitations, we introduce a novel stage-wise framework named PATCH. Specifically, we first augment the buggy code snippet with corresponding dependence context and intent information to better guide LLMs in generating the correct candidate patches. Additionally, by taking inspiration from bug management practices, we decompose the bug-fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to simulate the collaborative behavior of programmers during the resolution of software bugs. By harnessing these collective contributions, PATCH effectively enhances the bug-fixing capability of LLMs. We implement PATCH by employing the powerful dialogue-based LLM ChatGPT. Our evaluation on the widely used bug-fixing benchmark BFP demonstrates that PATCH has achieved better performance than state-of-the-art LLMs.

关键词： Bug Fixing Large Language Model Bug Management Multi-Agent Collaboration

来源：评论

学校读者我要写书评

暂无评论

A new Technique in Protein Structure Quantitative Identification

引用

Procedia computer science 2022年 214卷 1546-1553页

作者： Mengjiao Guo Haobin Cao Jing He Tengfei Ji Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne 3122 Australia Department of mechanical engineering University College London London WC1E 6BT United Kingdom Department of Neuroscience University of Oxford Oxford OX39DU United Kingdom State Key Laboratory of Bioactive Substance and Function of Natural Medicines Institute of Materia Medica Peking Union Medical College and Chinese Academy of Medical Sciences Beijing 100050 China

Graph distance is also named approximate graph isomorphism, error-tolerant graph matching, it is a measure of similarity (or dissimilarity) between two graphs. The graph distance function is an elusive question remaining a pressing problem in a wide range of fields. In general, graphs are usually enriched with node and edge attributes, namely, heterogeneous graphs, our focus is encapsulating node and edge identities in a graph. In addition, an adequate representation of the graph-adjacency matrix can capture the connectivity of the graph structure, while an adjacency matrix bears high-order combinatorial nature. Solving these challenges in the effective analysis of these graphs is of utmost importance. In this paper, structural and semantic features are both preserved by graphs, so the analysis of row sum and eigenspectra for vertex and edge adjacency matrix has captured the affinity interactions within graphs locally and globally. Therefore, we estimate the geometrical and semantic dissimilarities/distances between graphs extensively and systemically. Several illustrative chemical compound cases implement in practical scenarios, thus, the theory could be easily understood. Our method defines a quantitative distance (or dissimilarity) measure for comparing graphs, it has a good measure of expressiveness and a suited polynomial computation complexity, which paves the way for graph 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：