检索结果-内蒙古大学图书馆

International Conference on computer Science and Service System

作者： Zhang, Zhizheng School of Computer Science and Engineering Southeast University Nanjing 210096 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou University China

ISBN: (纸本)9781424497638

Both preference logics and preference representation in logic programming are concerned with reasoning about preferences on combinatorial domains, yet little research has been published using preference axioms in logic programming with preferences. In this paper, we propose a rational semantic for prioritized logic programming by combining rational preference with ideas underlying answer set programming. The rational semantics can implement a pervasive prioritized reasoning idea: The more preferential the precondition is, the more preferential the conclusion is. Rational preference logic is used to modeling the behavior of a rational agent. In this paper, we use rational preference axioms as the preference propagation principles. © 2011 IEEE.

关键词： Logic programming

来源：评论

学校读者我要写书评

暂无评论

Earth mover’s distance minimization for unsupervised bilingual lexicon induction

Earth mover’s distance minimization for unsupervised biling...

引用

2017 Conference on Empirical Methods in Natural Language processing, EMNLP 2017

作者： Zhang, Meng Liu, Yang Luan, Huanbo Sun, Maosong State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China

ISBN: (纸本)9781945626838

Cross-lingual natural language processing hinges on the premise that there exists invariance across languages. At the word level, researchers have identified such invariance in the word embedding semantic spaces of different languages. However, in order to connect the separate spaces, cross-lingual supervision encoded in parallel data is typically required. In this paper, we attempt to establish the cross-lingual connection without relying on any cross-lingual supervision. By viewing word embedding spaces as distributions, we propose to minimize their earth mover’s distance, a measure of divergence between distributions. We demonstrate the success on the unsupervised bilingual lexicon induction task. In addition, we reveal an interesting finding that the earth mover’s distance shows potential as a measure of language difference. © 2017 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Safety decision of autonomous driving behavior based on Bayesian network and its verification method 24

Safety decision of autonomous driving behavior based on Baye...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Li, Zexin Zhu, Yi Zhao, Li Zhao, Ying School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou China Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Jiangsu Nanjing China

ISBN: (纸本)9798350365658

With the increasing visibility of autonomous vehicles, the assurance of safe and precise behavioral decisions presents a substantial challenge within the realm of autonomous driving. The complexity of physical space, uncertainty in duration-space data, and human subjectivity complicate the assurance of existing behavior decision-making methods. To address these challenges, a safety decision method for autonomous driving based on Bayesian network is proposed. Firstly, semantic relations among risk elements in driving scenario are represented using knowledge graph, and the hierarchical structure and node information of the Bayesian network are determined based on expert knowledge and historical experience. Behavior decision actions are derived through Bayesian network inference. Secondly, leveraging the Bayesian network structure and inference results, a Duration-space Resource Timed Communicating Sequential process is construct to verify the security of time and space resources. Thirdly, the constructed process is converted into Bigraphs and use the CPS MODEL CHECKER for security verification. Finally, the effectiveness of the proposed method is verified using a highway lane change overtaking scenario. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A processing method for inconsistent answer set programs based on minimal principle

A processing method for inconsistent answer set programs bas...

引用

International Conference on Automatic Control and Artificial Intelligence, ACAI 2012

作者： Zhu, Tao Zhang, Zhizheng Zhai, Yuqing Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou University Suzhou China

ISBN: (纸本)9781849195379

Answer set programming (ASP) has become an important tool for knowledge representation and reasoning. Inconsistency processing in ASP provides a way for reasoning of inconsistent knowledge. In this paper, we present a minimal principle based method to process inconsistency in ASP. The method is able to ensure maximum retention of certain knowledge by removing the fewest defeasible rules preferentially. Then, we propose corresponding algorithms for simple logic programs and extended logic programs, and analyze the complexity of our method. After that, we compare this method with related work. Finally, we conclude and indicate the prospect of the further research.

关键词： processing

来源：评论

学校读者我要写书评

暂无评论

Exploiting Unlabeled Data for Neural Grammatical Error Detection

引用

Journal of computer Science & technology 2017年第4期32卷 758-767页

作者： Zhuo-Ran Liu Yang Liu School of Software Beihang University Beijing 100191 China State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 China Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Jiangsu Collaborative Innovation Center for Language Competence Xuzhou 221009 China

Identifying and correcting grammatical errors in the text written by non-native writers have received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVM and convolutional networks with fixed-size context window.

关键词： unlabeled data grammatical error detection neural network

来源：评论

学校读者我要写书评

暂无评论

A Model-Agnostic Interpretability Approach Based on Enhanced Hierarchical Clustering 24

A Model-Agnostic Interpretability Approach Based on Enhanced...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Ding, Xi Zhu, Yi Yu, Qiao Huang, Chongyang School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou China Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Jiangsu Nanjing China

ISBN: (纸本)9798350365658

The Local Interpretable Model-Agnostic Explanations (LIME) is a relatively novel technique for explaining black-box models. LIME generates perturbed instances of the model based on a random instance, and then approximates the original model with a linear model derived from the weighted perturbed instances, thereby providing an explanation for individual predictions. While LIME effectively addresses the opacity of black-box models, the randomness in instance generation often leads to unstable and inaccurate predictions. For a given prediction, different explanations may be generated, posing critical issues, particularly in security-sensitive domains. In response to these challenges, we propose a stable version of LIME, named DDLIME(Density and Distance-based LIME). DDLIME leverages improved hierarchical clustering and KNN algorithms to select instances that are most similar to the data, thus reducing the impact of perturbations. Additionally, the enhanced hierarchical clustering, incorporating density and distance metrics, enables DDLIME to address the limitations of traditional hierarchical clustering in clustering non-spherical clusters. Consequently, DDLIME can effectively capture complex structures and patterns within the data. The experimental results on three binary public datasets from the UCI repository demonstrate that DDLIME provides more stable explanations compared to LIME. Furthermore, compared to both baseline models, DDLIME exhibits superior performance across various evaluation metrics. © 2024 IEEE.

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Interest-Aware Message-Passing GCN for Recommendation 24

A Dynamic Interest-Aware Message-Passing GCN for Recommendat...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： He, Weichao Zhu, Yi Song, Mei Wu, Zixin Hao, Guosheng School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou China Jiangsu Engineering Technology Research Center of Ict in Education Jiangsu Xuzhou China Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Jiangsu Nanjing China

ISBN: (纸本)9798350365658

Over the past few years, Graph Convolutional Networks (GCN) have emerged as a promising tool in the field of recommendation. They have the ability to effectively learn user and item embeddings by leveraging collaborative signals from higher-order neighbors. Nevertheless, the recommendation models based on GCN also face a common issue. As more layers are added, the node embeddings start to become increasingly similar and eventually become indistin-guishable, leading to a decline in performance. To address the issues at hand, we present a recommendation model called DIMP-GCN. This model utilizes a Dynamic Interest-aware Message-Passing approach, where users and interacted items are organized into distinct subgraphs based on their interests. Within each subgraph, single-layer graph convolution operations are performed. As a result, the users who have been updated are divided based on their interests once again, leading to dynamic changes in subgraph partitioning as the network layers stack. Nodes are able to acquire more accurate representations through this process. We conduct extensive experiments on three established datasets, showcasing the superior performance of our DIMP-GCN compared to other state-of-the-art GCN-based recommendation models. © 2024 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Edge Service Optimization in Internet of Vehicles:A Survey

引用

Tsinghua Science and technology 2022年第2期27卷 270-287页

作者： Xiaolong Xu Haoyuan Li Weijie Xu Zhongjian Liu Liang Yao Fei Dai the School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China the Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science and Technology and EngineeringNanjing 210044China the State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China the School of Big Data and Intelligence Engineering Southwest Forestry UniversityKunming 650233China

The Internet of Vehicles(IoV)plays a crucial role in providing diversified services because of its powerful capability of collecting real-time ***,collected information is transmitted to a centralized resourceintensive cloud platform for service *** Computing(EC)that deploys physical resources near road-side units is involved in IoV to support real-time services for vehicular ***,many measures are adopted to optimize the performance of EC-enabled IoV,but they hardly help make dynamic decisions according to real-time *** Intelligence(AI)is capable of enhancing the learning capacity of edge devices and thus assists in allocating resources *** extensive research has employed AI to optimize EC performance,summaries with relative concepts or prospects are quite *** address this gap,we conduct an exhaustive survey about utilizing AI in edge service optimization in ***,we establish the general condition and relative concepts about IoV,EC,and ***,we review the edge service frameworks for IoV and explore the use of AI in edge server placement and service ***,we discuss a number of open issues in optimizing edge services with AI.

关键词： edge service internet of vehicles artificial intel igence

来源：评论

学校读者我要写书评

暂无评论

A decoupled hybrid structure for active noise control with uncorrelatednarrowband disturbances 43

A decoupled hybrid structure for active noise control with u...

引用

43rd International Congress on Noise Control Engineering: Improving the World Through Noise Control, INTERNOISE 2014

作者： Wu, Lifu Qiu, Xiaojun Burnett, Ian S. Cheng, Eva Guo, Yecai Royal Melbourne Institute of Technology School of Electrical and Computer Engineering Australia Jiangsu Key Laboratory of Meteorological Observation and Information Processing Nanjing University of Information Science and Technology 210044 China

ISBN: (纸本)9780909882037

In real active noise control (ANC)applications,the following situations frequently occur, one isthat disturbances only present at the error sensor and havelowcorrelation with reference signal, the other is thatthere is no enough space or ideal position for locating the reference sensor to satisfy causality condition. Thusthe residual noise after feedforward control can be seen as uncorrelated narrowband disturbancesin these situationsand ahybrid adaptive feedforward and feedback structure is often utilized to cope with this *** efforts have been paid to improve the performance of the hybrid ANC system, nevertheless, few interests are concerned about the combination method between the feedforward and feedback structure. After investigating the conventional combination method of hybrid feedforward and feedback system, this paper introduces analternate combination method for hybrid ANC systemwhich featuresthat itavoidsthe coupling between the feedforward and feedback structures and both structures are concatenated to attenuate the ambient noise. Simulations are carried out to validatethe effectiveness of the introduced methodfor ANCwith uncorrelated narrowband disturbances.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Reliable neighbors-based collaborative filtering for recommendation systems 1

引用

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Zhang, Li Sun, Xiaohan Cheng, Jiangfei Li, Zepeng School of Computer Science and Technology Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Soochow University SuzhouJiangsu215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University SuzhouJiangsu215006 China

ISBN: (数字)9789811576706

ISBN: (纸本)9789811576690

The sparsity of data and the diversity of ratings have a great effect on the performance of recommendation systems. To deal with these two issues, this paper proposes a reliable neighbors-based collaborative filtering (RNCF) method for recommendation systems. RNCF first uses the item similarity to pre-estimated missing ratings to solve the issue of data sparsity, which enriches the sample data and reduces the impact of extremely sparse ratings on the recommendation effect. Then, RNCF finds a set of reliable users for each item by defining a reliable degree for each item. Next, RNCF adopts the K-means clustering algorithm to find the similar users for a target user. The set of reliable neighbors is the intersection of sets of reliable users and similar users. Finally, RNCF provides a predicted rating of a target user on some item using the pre-estimated ratings of corresponding reliable neighbors. Experimental analysis shows that RNCF can improve the performance at the extreme levels of sparsity and rating diversity in recommendation systems. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Collaborative filtering

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：