检索结果-内蒙古大学图书馆

Program generic set:semantics of medium logic program described by forcing

science China(Technological sciences) 1996年第6期39卷 620-627页

作者：朱朝晖施庆生朱梧槚 Institute of Computer Science Nanjing University of Aeronautics and AstronauticsNanjing 210016China Department of Basic Sciences Nanjing Architectural and Civil Engineering InstituteNanjing 210009China State Key Laboratory for Novel Software Technology at Nanjing University Nanjing 210093China Institute of Computer ScienceNanjing University of Aeronautics and AstronauticsNanjing 210016China

The technique of forcing created by Cohen is adopted to discuss the semantics of medium logic program without closed-world assumption (CWA).The fixed point and complete-meet semilattice property ofprogram generic set ... 详细信息

关键词： medium logic program semantics non-CWA program generic set.

来源：评论

学校读者我要写书评

暂无评论

Cost-Efficient Deep Neural Network Placement in Edge Intelligence-Enabled Internet of Things

引用

ACM Transactions on Sensor Networks 1000年

作者： Hao Tian Xiaolong Xu Hongyue Wu Qingzhan Zhao Jianguo Dai Maqbool Khan State Key Laboratory for Novel Software Technology Nanjing University Nanjing Jiangsu China Nanjing China School of Software Nanjing University of Information Science and Technology Nanjing Jiangsu China Nanjing China College of Intelligence and Computing Tianjin University Tianjin China Tianjin China Geospatial Information Engineering Research Center College of Information Science and Technology Shihezi University Shihezi Xinjiang China Shihezi China Department of IT and Computer Science Pak-Austria Fachhochschule Institute of Applied Sciences and Technology Haripur Pakistan Haripur Pakistan

Edge intelligence (EI) integrates edge computing and artificial intelligence empowering service providers to deploy deep neural networks (DNNs) on edge servers in proximity to users to provision intelligent applications (e.g., autonomous driving) for ubiquitous Internet of Things (IoT) in smart cities, which facilitates the quality of experience (QoE) of users and improves the processing and energy efficiency. However, considering DNN is typically computational-intensive and resource-hungry, conventional placement approaches ignore the influence of multi-dimensional resource requirements (processor, memory, etc.), which may degrade the real-time performance. Moreover, with the increasing scale of geo-distributed edge servers, centralized decision-making is still challenging to find the optimal strategies effectively. To overcome these shortcomings, in this paper we propose a game theoretic DNN placement approach in EI-enabled IoT. First, a DNN placement optimization problem is formulated to maximize system benefits, which is proven to be \(\mathcal {N}\mathcal {P}\)-hard and model the original problem as an exact potential game (EPG). Moreover, an EPG-based DNN model placement algorithm, named EPOL, is designed for edge servers to make sub-optimal strategies independently and theoretical analysis is possessed to guarantee the performance of EPOL. Finally, real-world dataset based experimental results corroborate the superiority and effectiveness of EPOL.

关键词： Edge intelligence DNN placement Game theory Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Code Simplification Methods in Code Intelligence Tasks

引用

ACM Transactions on software Engineering and Methodology 1000年

作者： Zongwen Shen Yuning Li Jidong Ge Xiang Chen Chuanyi Li Liguo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence and Computer Science Nantong University China Department of Computer Science Southern Methodist University USA National Key Laboratory for Novel Software Technology at Nanjing University China

In recent years, pre-trained language models have seen significant success in natural language processing and have been increasingly applied to code-related tasks. Code intelligence tasks have shown promising performance with the support of code pre-trained language models. Pre-processing code simplification methods have been introduced to prune code tokens from the model’s input while maintaining task effectiveness. These methods improve the efficiency of code intelligence tasks while reducing computational costs. Post-prediction code simplification methods provide explanations for code intelligence task outcomes, enhancing the reliability and interpretability of model predictions. However, comprehensive evaluations of these methods across diverse code pre-trained model architectures and code intelligence tasks are lacking. To assess the effectiveness of code simplification methods, we conduct an empirical study integrating these code simplification methods with various pre-trained code models across multiple code intelligence *** empirical findings suggest that developing task-specific code simplification methods would be beneficial. Then, we recommend leveraging post-prediction methods to summarize prior knowledge, which can pre-process code simplification strategies. Moreover, establishing more evaluation mechanisms for code simplification is crucial. Finally, we propose incorporating code simplification methods into the pre-training phase of code pre-trained models to enhance their program comprehension and code representation capabilities.

关键词： Code Simplifications Code Pre-train Models Code intelligence tasks Program representations

来源：评论

学校读者我要写书评

暂无评论

software Engineering and Methodology for Emerging Domains 1

引用

丛书名： Communications in computer and Information science

1000年

作者： Lu Zhang Chang Xu

来源：评论

学校读者我要写书评

暂无评论

Advances in Artificial Reality and Tele-Existence 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Zhigeng Pan Adrian Cheok Michael Haller Rynson W. H. Lau Hideo Saito Ronghua Liang

ISBN: (数字)9783540497790

ISBN: (纸本)9783540497769

ICAT is the oldest international conference on virtual reality and tele-existence. ICAT 2006 not only looked for innovations in the technology itself, but also explored novel ways to transfer and express information and creative ideas to the society and people. The 16th International Conference on Artificial Reality and Telexistence was held at the Zhejiang University of technology, Hangzhou, P. R. China from November 29 to December 1, 2006. The main purpose of the conference is to provide opportunities for researchers and practitioners to present their research findings and exchange opinions on the development and use of such systems. The conference included plenary invited talks, workshops, tutorials, and paper presentation tracks. The main conference received 523 submissions in total from 21 different countries, including China (mainland, Hong Kong, Taiwan), USA, UK, Germany, Austria, France, Australia, Canada, Korea, Japan, Malaysia, Mexico, etc. , of which 138 papers were accepted for this volume and 11 papers were invited to submit extended versions for a special issue of International Journal of Virtual Reality (IJVR, 5(4)).

关键词： User Interfaces and Human computer Interaction Artificial Intelligence Information Systems Applications (incl. Internet) Multimedia Information Systems Image Processing and computer Vision computer Appl. in Arts and Humanities

来源：评论

学校读者我要写书评

暂无评论

Intelligent science and Intelligent Data Engineering 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Yanning Zhang Ying Li Zhi-Hua Zhou Changshui Zhang

ISBN: (数字)9783642319198

ISBN: (纸本)9783642319181

This book constitutes the proceedings of the Sino-foreign-interchange Workshop on Intelligence science and Intelligent Data Engineering, IScIDE 2011, held in Xi'an, China, in October 2011. The 97 papers presented were carefully peer-reviewed and selected from 389 submissions. The IScIDE papers in this volume are organized in topical sections on machine learning and computational intelligence; pattern recognition; computer vision and image processing; graphics and computer visualization; knowledge discovering, data mining, web mining; multimedia processing and application.

关键词： Image Processing and computer Vision Pattern Recognition computer Graphics Artificial Intelligence Multimedia Information Systems Data Mining and Knowledge Discovery

来源：评论

学校读者我要写书评

暂无评论

Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models

引用

ACM Transactions on software Engineering and Methodology 1000年

作者： Quanjun Zhang Chunrong Fang Yi Zheng Yaxin Zhang Yuan Zhao Rubing Huang Jianyi Zhou Yun Yang Tao Zheng Zhenyu Chen Department of Computing Technologies Swinburne University of Technology Australia and State Key Laboratory for Novel Software Technology Nanjing University China State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Macau University of Science and Technology China Huawei Cloud Computing Technologies Co. Ltd. China Department of Computing Technologies Swinburne University of Technology Australia State Key Laboratory for Novel Software Technology Nanjing University China and Shenzhen Research Institute of Nanjing University China

Unit testing validates the correctness of the units of the software system under test and serves as the cornerstone in improving software quality and reliability. To reduce manual efforts in writing unit tests, some techniques have been proposed to generate test assertions automatically, including deep learning (DL)-based, retrieval-based, and integration-based ones. Among them, recent integration-based approaches inherit from both DL-based and retrieval-based approaches and are considered state-of-the-art. Despite being promising, such integration-based approaches suffer from inherent limitations, such as retrieving assertions with lexical matching while ignoring meaningful code semantics, and generating assertions with a limited training *** this paper, we propose a novel Retrieval-Augmented Deep Assertion Generation approach, namely RetriGen, based on a hybrid assertion retriever and a pre-trained language model (PLM)-based assertion generator. Given a focal-test, RetriGen first builds a hybrid assertion retriever to search for the most relevant test-assert pair from external codebases. The retrieval process takes both lexical similarity and semantical similarity into account via a token-based and an embedding-based retriever, respectively. RetriGen then treats assertion generation as a sequence-to-sequence task and designs a PLM-based assertion generator to predict a correct assertion with historical test-assert pairs and the retrieved external assertion. Although our concept is general and can be adapted to various off-the-shelf encoder-decoder PLMs, we implement RetriGen to facilitate assertion generation based on the recent CodeT5 model. We conduct extensive experiments to evaluate RetriGen against six state-of-the-art approaches across two large-scale datasets and two metrics. The experimental results demonstrate that RetriGen achieves 57.66% and 73.24% in terms of accuracy and CodeBLEU, outperforming all baselines with an average improvement of 50.66%

关键词： Unit Testing Assertion Generation Pre-trained Language Models AI4SE

来源：评论

学校读者我要写书评

暂无评论

Parallel and Distributed Processing and Applications 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Yi Pan Daoxu Chen Minyi Guo Jiannong Cao Jack Dongarra

ISBN: (数字)9783540321002

ISBN: (纸本)9783540297697

Welcome to the proceedings of ISPA 2005 which was held in the city of Nanjing. Parallel computing has become a mainstream research area in computer science and the ISPA conference has become one of the premier forums for the presentation of new and exciting research on all aspects of parallel computing. We are pleased to present the proceedings for the 3rd International Symposium on Parallel and Distributed Processing and Applications (ISPA 2005), which comprises a collection of excellent technical papers, and keynote speeches. The papers accepted cover a wide range of exciting topics, including architectures, software, networking, and applications. The conference continues to grow and this year a record total of 968 manuscripts (including workshop submissions) were submitted for consideration by the Program Committee or workshops. From the 645 papers submitted to the main conference, the Program Committee selected only 90 long papers and 19 short papers in the program. Eight workshops complemented the outstanding paper sessions.

关键词： computer System Implementation Algorithm Analysis and Problem Complexity computer Communication Networks Information Systems Applications (incl. Internet) System Performance and Evaluation software Engineering

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Parameter-Efficient Fine-Tuning for software Engineering Tasks

引用

ACM Transactions on software Engineering and Methodology 1000年

作者： Wentao Zou Zongwen Shen Qi Li Jidong Ge Chuanyi Li Xiang Chen Xiaoyu Shen LiGuo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence and Computer Science Nantong University China Eastern Institute for Advanced Study China Department of Computer Science Southern Methodist University USA

Pre-trained models (PTMs) have succeeded in various software engineering (SE) tasks following the “pre-train then fine-tune” paradigm. As fully fine-tuning all parameters of PTMs can be computationally expensive, a potential solution is parameter-efficient fine-tuning (PEFT), which freezes PTMs while introducing extra parameters. Although PEFT methods have been applied to SE tasks, researchers often focus on specific scenarios and lack a comprehensive comparison of PTMs from different aspects such as field, size, and architecture. To fill this gap, we have conducted an empirical study on six PEFT methods, eight PTMs, and four SE tasks. The experimental results reveal several noteworthy findings. For example, model architecture has little impact on PTM performance when using PEFT methods. Additionally, we provide a comprehensive discussion of PEFT methods from three perspectives. First, we analyze the effectiveness and efficiency of PEFT methods. Second, we explore the impact of the scaling factor hyperparameter. Finally, we investigate the application of PEFT methods on the latest open-source large language model, Llama 3.2. These findings provide valuable insights to guide future researchers in effectively applying PEFT methods to SE tasks.

关键词： parameter-efficient fine-tuning pre-trained model software engineering task empirical study effectiveness and efficiency

来源：评论

学校读者我要写书评

暂无评论

Model Pruning-enabled Federated Split Learning for Resource-constrained Devices in Artificial Intelligence Empowered Edge Computing Environment

引用

ACM Transactions on Sensor Networks 1000年

作者： Yongzhe Jia Bowen Liu Xuyun Zhang Fei Dai Arif Khan Lianyong Qi Wanchun Dou State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China Department of Computing Macquarie University Sydney Australia College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China M3S Empirical Software Engineering Research Unit University of Oulu Oulu Finland College of Computer Science and Technology China University of Petroleum East China - Qingdao Campus Qingdao China

Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by smart devices. However, parallel DCML frameworks require resource-constrained devices to update the entire Deep Neural Network (DNN) models and are vulnerable to reconstruction attacks. Concurrently, the serial DCML frameworks suffer from training efficiency problems due to their serial training nature. In this paper, we propose a Model Pruning-enabled Federated Split Learning framework (MP-FSL) to reduce resource consumption with a secure and efficient training scheme. Specifically, MP-FSL compresses DNN models by adaptive channel pruning and splits each compressed model into two parts that are assigned to the client and the server. Meanwhile, MP-FSL adopts a novel aggregation algorithm to aggregate the pruned heterogeneous models. We implement MP-FSL with a real FL platform to evaluate its performance. The experimental results show that MP-FSL outperforms the state-of-the-art frameworks in model accuracy by up to 1.35%, while concurrently reducing storage and computational resource consumption by up to 32.2% and 26.73%, respectively. These results demonstrate that MP-FSL is a comprehensive solution to the challenges faced by DCML, with superior performance in both reduced resource consumption and enhanced model performance.

关键词： Federated learning split learning model pruning edge computing

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：