检索结果-内蒙古大学图书馆

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

engineering 2025年

作者： Qinghua Zheng Huan Liu Xiaoqing Zhang Caixia Yan Xiangyong Cao Tieliang Gong Yong-Jin Liu Bin Shi Zhen Peng Xiaocen Fan Ying Cai Jun Liu School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Translational Research Institute of Brain and Brain-Like Intelligence Shanghai Fourth People’s Hospital Shanghai 200434 China School of Medicine Tongji University Shanghai 200092 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science Iowa State University Ames IA 50011 USA

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M 2 I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M 2 I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M 2 I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词： Machine memory intelligence Neural mechanism Associative representation Continual learning Collaborative reasoning

来源：评论

学校读者我要写书评

暂无评论

The Integrated Use of Business Continuity Management Systems, Records Management Systems and knowledge Management Systems

The Integrated Use of Business Continuity Management Systems...

引用

International Conference on Management and Service Science, MASS

作者： Xiaomi An Wang Wang Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Renmin University of China Beijing China School of Information Resource Management Renmin University of China Beijing China

Much research has been done on integrated use of ISO management system standards. Integrated use of management systems is identified to have shared values of varied integration impacts on resources efficiency building and sustainable development of business processes. However, little research has been done on integrated use of business continuity management systems (BCMS), records management systems (RMS) and knowledge management systems (KMS). This paper proposes a holistic integration management approach for collaboration, optimization and innovation of the three management systems through mapping/building/operationalizing cycle for supply of efficiency building strategy to the dynamic accumulation, sharing, and exchanges of memory, evidence and knowledge of organization.

关键词： ISO standards Collaboration knowledge management Standards organizations Organizations

来源：评论

学校读者我要写书评

暂无评论

TABLELLM: Enabling Tabular data Manipulation by LLMs in Real Office Usage Scenarios

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaokang Luo, Sijia Zhang, Bohan Ma, Zeyao Zhang, Jing Li, Yang Li, Guanlin Yao, Zijun Xu, Kangli Zhou, Jinchang Zhang-Li, Daniel Yu, Jifan Zhao, Shu Li, Juanzi Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Computer Science Anhui University China

We introduce TABLELLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TABLELLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TABLELLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Copyright © 2024, The Authors. All rights reserved.

关键词： Spreadsheets

来源：评论

学校读者我要写书评

暂无评论

Against Code Injection with System Call Randomization

Against Code Injection with System Call Randomization

引用

International Conference on Networks Security, Wireless Communications and Trusted Computing, NSWCTC

作者： Zhaohui Liang Bin Liang Luping Li Wei Chen Qingqing Kang Yingqin Gu Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Beijing China Renmin University of China Beijing CN School of Information Renmin University of China China

ISBN: (纸本)9781424442232

The existing code injection attack defense methods have some deficiencies on performance overhead and effectiveness. In order to ensure the system performance, we propose a method that uses system call randomization to counter code injection attacks based on instruction set randomization idea. An injected code would perform its actions with system calls. System call randomization on operating system level will prevent the injected code from executing correctly. Moreover, with an extended compiler, our method can perform source code randomization during compiling and implement binary executable files randomization by feature matching. The experiments show that our method can effectively counter variety code injection attacks with low overhead.

关键词： Equations Counting circuits Operating systems Kernel Communication system security data security Information security Wireless communication Computer networks Laboratories

来源：评论

学校读者我要写书评

暂无评论

A decomposition method to solve the large-scale scheduling problems based on cellular manufacturing technology

A decomposition method to solve the large-scale scheduling p...

引用

2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, AIMSEC 2011

作者： Niu, Li Han, Xiaoting Data Engineering and Knowledge Engineering Key Laboratory School of Information Resource Management Renmin University of China Beijing China School of Economics and Management Beihang University Beijing China

ISBN: (纸本)9781457705366

A decomposition method to solve the large-scale scheduling problems is proposed in this paper. Focused on largescale scheduling problems, introducing cellular manufacturing technology to decompose scheduling problems, a collaborative scheduling process based on manufacturing cells is designed. Moreover, focused on the coupling problem in scheduling process in the context of cellular manufacturing, a decomposition method is suggested to achieve the decomposition of cross-cell jobs. Finally, the whole scheduling process is simplified through redefining the environment of cellular manufacturing. © 2011 IEEE.

关键词： Cellular manufacturing

来源：评论

学校读者我要写书评

暂无评论

DAGKT: Difficulty and Attempts Boosted Graph-based knowledge Tracing

arXiv

引用

arXiv 2022年

作者： Luo, Rui Liu, Fei Liang, Wenhao Zhang, Yuhong Bu, Chenyang Hu, Xuegang Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China School of Computer Science and Information Engineering Hefei University of Technology China Jianzai Tech Hefei China

In the field of intelligent education, knowledge tracing (KT) has attracted increasing attention, which estimates and traces students’ mastery of knowledge concepts to provide high-quality education. In KT, there are natural graph structures among questions and knowledge concepts so some studies explored the application of graph neural networks (GNNs) to improve the performance of the KT models which have not used graph structure. However, most of them ignored both the questions’ difficulties and students’ attempts at questions. Actually, questions with the same knowledge concepts have different difficulties, and students’ different attempts also represent different knowledge mastery. In this paper, we propose a difficulty and attempts boosted graph-based KT (DAGKT)3, using rich information from students’ records. Moreover, a novel method is designed to establish the question similarity relationship inspired by the F1 score. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed DAGKT. Copyright © 2022, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Random Access to Hierarchically-Compressed data

Enabling Efficient Random Access to Hierarchically-Compresse...

引用

International Conference on data engineering

作者： Feng Zhang Jidong Zhai Xipeng Shen Onur Mutlu Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Department of Computer Science and Technology Tsinghua University BNRist Computer Science Department North Carolina State University Department of Computer Science ETH Zürich

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129044

Recent studies have shown the promise of direct data processing on hierarchically-compressed text documents. By removing the need for decompressing data, the direct data processing technique brings large savings in both time and space. However, its benefits have been limited to data traversal operations; for random accesses, direct data processing is several times slower than the state-of-the-art baselines. This paper presents a set of techniques that successfully eliminate the limitation, and for the first time, establishes the feasibility of effectively handling both data traversal operations and random data accesses on hierarchically-compressed data. The work yields a new library, which achieves 3.1× speedup over the state-of-the-art on random data accesses to compressed data, while preserving the capability of supporting traversal operations efficiently and providing large (3.9×) space savings.

关键词： Indexing data processing data structures Technological innovation Dictionaries Law data mining

来源：评论

学校读者我要写书评

暂无评论

Quantifying Interactions between Layers in Duplex Networks Using Interactive Entropy

引用

Journal of Library & Information Studies 2020年第2期18卷 31-41页

作者： Zhang, Ronda J. Ye, Fred Y. International Joint Informatics Laboratory (IJIL) Nanjing University - University of Illinois Nanjing-Champaign Nanjing China Jiangsu Key Laboratory of Data Engineering and Knowledge Service School of Information Management Nanjing University Nanjing China

The multiplex network has attracted wide attention because it can better describe the various relationships in the real world, and the duplex network is a special two-layer form of it. The purpose of this research focuses on introducing new entropy-based measures for multiplex network, especially duplex network. The new measure called Interactive entropy in duplex network (IE) is based on information entropy, a key concept of information theory. It can be applied to various types of multiplex networks to quantify the differences between the layers of inside duplex network. [ABSTRACT FROM AUTHOR]

关键词： Duplex Network Interactive Entropy Multiplex Network

来源：评论

学校读者我要写书评

暂无评论

Sampling Topic Representative Users by Integrating Node Degree and Edge Weight

Sampling Topic Representative Users by Integrating Node Degr...

引用

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Jiangwen Wang Zhijie Ban Inner Mongolia A.R. Key Laboratory of Data Mining and Knowledge Engineering College of Computer Science Inner Mongolia University Huhhot China

ISBN: (数字)9781728195582

ISBN: (纸本)9781728195599

Finding a subset of users to statistically represent the original social network in terms of attributes has received a lot of attention recently. The existing literature had proved that the problem is NP-Hard and proposed some sampling models, but representative degrees aren't systematically studied. Taking node degree and edge weight into account, we present a topic sampling model for the whole social network in this paper. Firstly, by statistically calculating node degrees for one real dataset, we find that one node is more likely to be a representative user if its degree is high. We then give some definitions about representative degrees. Based on statistical stratified sample, we finally give a sampling model of topic representative users who are from most or all attribute groups in the network. Experimental results show that our algorithm significantly outperforms other six baseline methods and is also effective in terms of time complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Static vulnerabilities detection method based on security state tracing and checking

引用

Jisuanji Xuebao/Chinese Journal of Computers 2009年第5期32卷 899-909页

作者： Liang, Bin Hou, Kan-Kan Shi, Wen-Chang Liang, Zhao-Hui School of Information Renming University of China Beijing 100872 China MOE Key Laboratory of Data Engineering and Knowledge Engineering Beijing 100872 China

The main problem of existing static vulnerability detection methods based source code analysis is their high false positive and false negative rates. One main reason is lack of accurate and effective identification and analysis of security-related program elements, e.g. data validation checking, tainted data source, etc. A static vulnerability detection method based on data security state tracing and checking is proposed. In this method, the state space of state machine model is extended;the security state of a variable is identified by a vector that may correspond to multiple security-related properties rather than by a single property;Fine-grained state transition is provided to support accurate recognition of program security-related behaviors;The recognition of validation checking is introduced in vulnerability state machine to reduce false positives;and a systematic discrimination mechanism for tainted data is constructed to prevent false negatives result from neglecting tainted data sources. The experimental results of a prototype system show that this method can effectively detect buffer overflow and other type's vulnerabilities in software systems, and with obviously lower false positive than existing mainstream static detection methods and avoid some serious false negatives of these methods.

关键词： Static 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：