检索结果-内蒙古大学图书馆

Proceedings of the 37th IEEE/ACM International Conference on Automated software engineering

作者： Nghi D. Q. Bui Yijun Yu Trustworthy Software Engineering & Open Source Lab Huawei Ireland Research Center Ireland

ISBN: (纸本)9781450394758

Existing approaches to improving the robustness of source code models concentrate on recognizing adversarial samples rather than valid samples that fall outside of a given distribution, which we refer to as out-of-distribution (OOD) samples. To this end, we propose to use an auxiliary dataset (out-of-distribution) such that, when trained together with the main dataset, they will enhance the model’s robustness. We adapt energy-bounded learning objective function to assign a higher score to in-distribution samples and a lower score to out-of-distribution samples in order to incorporate such out-of-distribution samples into the training process of source code models. In terms of OOD detection and adversarial samples detection, our evaluation results demonstrate a greater robustness for existing source code models to become more accurate at recognizing OOD data while being more resistant to adversarial attacks at the same time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations 21

Self-Supervised Contrastive Learning for Code Retrieval and ...

引用

44th International ACM SIGIR Conference on Research and Development in Information Retrieval

作者： Bui, Nghi D. Q. Yu, Yijun Jiang, Lingxiao Huawei Ireland Res Ctr Trustworthy Software Engn & Open Source Lab Dublin Ireland Open Univ Milton Keynes Bucks England Singapore Management Univ Sch Comp & Informat Syst Singapore Singapore

ISBN: (纸本)9781450380379

We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used in two ways: (1) it can produce vector representation of code which can be applied to code retrieval tasks that do not have labeled data;(2) it can be used in a fine-tuning process for tasks that might still require label data such as code summarization. The key innovation is that we train the source code model by asking it to recognize similar and dissimilar code snippets through a contrastive learning objective. To do so, we use a set of semantic-preserving transformation operators to generate code snippets that are syntactically diverse but semantically equivalent. Through extensive experiments, we have shown that the code models pretrained by Corder substantially outperform the other baselines for code-to-code retrieval, text-to-code retrieval, and code-to-text summarization tasks.

关键词： compiler code-summarization code-learning code-search source-code-model code-retrieval program-transformation big-code code-representation contrastive-learning

来源：评论

学校读者我要写书评

暂无评论

TreeCaps: Tree-Based Capsule Networks for source Code Processing 35

TreeCaps: Tree-Based Capsule Networks for Source Code Proces...

引用

35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence

作者： Bui, Nghi D. Q. Yu, Yijun Jiang, Lingxiao Huawei Res Ctr Trustworthy Open Source Software Engn Lab Dublin Ireland Open Univ Sch Comp & Commun Milton Keynes Bucks England Singapore Management Univ Sch Comp & Informat Syst Singapore Singapore

ISBN: (纸本)9781577358664

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., abstract syntax trees) and/or semantic information (e.g., dependency graphs). While graphs may be better than trees at capturing code semantics, constructing the graphs from code inputs through the semantic analysis of multiple viewpoints can lead to inaccurate noises for a specific software engineering task. Compared to graphs, syntax trees are more precisely defined on the grammar and easier to parse;unfortunately, previous tree-based learning techniques have not been able to learn semantic information from trees to achieve better accuracy than graph-based techniques. We have proposed a new learning technique, named TreeCaps, by fusing together capsule networks with tree-based convolutional neural networks to achieve a learning accuracy higher than some existing graph-based techniques while it is based only on trees. TreeCaps introduces novel variable-to-static routing algorithms into the capsule networks to compensate for the loss of previous routing algorithms. Aside from accuracy, we also find that TreeCaps is the most robust to withstand those semantic-preserving program transformations that change code syntax without modifying the semantics. Evaluated on a large number of Java and C/C++ programs, TreeCaps models outperform prior deep learning models of program source code, in terms of both accuracy and robustness for program comprehension tasks such as code functionality classification and function name prediction. Our implementation is publicly available at: https://***/bdqnghi/treecaps.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Self-supervised contrastive learning for code retrieval and summarization via semantic-preserving transformations

arXiv

引用

arXiv 2020年

作者： Bui, Nghi D.Q. Yu, Yijun Jiang, Lingxiao Trustworthy Software Engineering and Open Source Lab Huawei Ireland Research Center Trustworthy Software Engineering and Open Source Lab Huawei Ireland Research Center Open University United Kingdom School of Computing and Information Systems Singapore Management University Singapore

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Training, testing and benchmarking medical AI models using Clinical AIBench

引用

BenchCouncil Transactions on Benchmarks, Standards and Evaluations 2022年第1期2卷 100037-100037页

作者： Huang, Yunyou Miao, Xiuxia Zhang, Ruchang Ma, Li Liu, Wenjing Zhang, Fan Guan, Xianglong Liang, Xiaoshuang Lu, Xiangjiang Tang, Suqing Zhang, Zhifei Guangxi Key Lab of Multi-Source Information Mining & Security School of Computer Science and Engineering & School of Software Guangxi Normal University Guilin China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Guilin Medical University Guilin China Department of Physiology and Pathophysiology Capital Medical University Beijing China Faculty of Education Guangxi Normal University Guilin China International Open Benchmark Council Beijing China

AI technology has been used in many clinical research fields, but most AI technologies are difficult to land in real-world clinical settings. In most current clinical AI research settings, the diagnosis task is to identify different types of diseases among the given ones. However, the diagnosis in real-world settings needs dynamically developing inspection strategies based on the existing resources of medical institutions and identifying different kinds of diseases out of many possibilities. To promote the development of different clinical AI technologies and the implementation of clinical applications, we propose a benchmark named Clinical AIBench for developing, verifying, and evaluating clinical AI technologies in real-world clinical settings. Specifically, Clinical AIBench can be used for: (1) Model training and testing: Researchers can use the data to train and test their models. (2)Model evaluation: Researchers can use Clinical AIBench to objectively, fairly, and comparably evaluate various models of different researchers. (3) Clinical value evaluation: Researchers can use the clinical indicators provided by Clinical AIBench to evaluate the clinical value of models, which will be applied in real-world clinical settings. For convenience, Clinical AIBench provides three different levels of clinical settings: restricted clinical setting, which is named closed clinical setting, data island clinical setting, and real-world clinical setting, which is called open clinical setting. In addition, Clinical AIBench covers three diseases: Alzheimer's disease, COVID-19, and dental. Clinical AIBench provides python APIs to researchers. The data and source code are publicly available from the project website https://***/clinical_aibench/. © 2022 The Authors

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

openClinicalAI: enabling AI to diagnose diseases in real-world clinical settings

arXiv

引用

arXiv 2021年

作者： Huang, Yunyou Wang, Nana Tang, Suqin Ma, Li Hao, Tianshu Jiang, Zihan Zhang, Fan Kang, Guoxin Miao, Xiuxia Guan, Xianglong Zhang, Ruchang Zhang, Zhifei Zhan, Jianfeng Guangxi Key Lab of Multi-Source Information Mining & Security School of Computer Science and Engineering School of Software Guangxi Normal University Guilin China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Guilin Medical University Guilin China Department of Physiology and Pathophysiology Capital Medical University Beijing China University of Chinese Academy of Sciences China International Open Benchmark Council

This paper quantitatively reveals the state-of-the-art and state-of-the-practice AI systems only achieve acceptable performance on the stringent conditions that all categories of subjects are known, which we call closed clinical settings, but fail to work in real-world clinical settings. Compared to the diagnosis task in the closed setting, real-world clinical settings pose severe challenges, and we must treat them differently. We build a clinical AI benchmark named Clinical AIBench to set up real-world clinical settings to facilitate researches. We propose an open, dynamic machine learning framework and develop an AI system named openClinicalAI to diagnose diseases in real-world clinical settings. The first versions of Clinical AIBench and openClinicalAI target Alzheimer’s disease. In the real-world clinical setting, openClinicalAI significantly outperforms the state-of-the-art AI system. In addition, openClinicalAI develops personalized diagnosis strategies to avoid unnecessary testing and seamlessly collaborates with clinicians. It is promising to be embedded in the current medical systems to improve medical services. © 2021, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Port embedded Linux to XUP Virtex-II Pro development board

Port embedded Linux to XUP Virtex-II Pro development board

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Qingguo Zhou Qi Yao Chanjuan Li Bin Hu Distributed & Embedded System Lab (DSLab) Lanzhou University China Engineering Research Center of Open Source Software and Real-Time Systems Ministry of Education Lanzhou University China

As its free, rich code resource and supporting many kinds of CPU architecture, Linux is making steady progress in the embedded arena. The Virtex-II Pro serials development system, produced by Xilinx company, provides an advanced hardware platform that consists of a high performance Virtex serials platform FPGA surrounded by a comprehensive collection of peripheral components that can be used to create a complex system and meet different special embedded application areas. This paper mainly introduces porting embedded Linux to the XUP Virtex- II Pro development system, and using serials of development tool kits. It is a good guide to develop embedded system with FPGA development system and Linux.

关键词： Linux Embedded system Field programmable gate arrays Hardware Kernel Embedded computing Computer architecture Power system reliability open source software Computer applications

来源：评论

学校读者我要写书评

暂无评论

A Case Study of Microkernel for Education

A Case Study of Microkernel for Education

引用

2009 IEEE International Symposium on IT in Medicine & Education(ITME2009)

作者： Nicholas McGuire Distributed & Embedded System Lab (DSLab) Lanzhou UniversityChina Engineering Research Center of Open Source Software and Real-Time Systems Ministry of EducationLanzhou UniversityChina

The paper will introduce a new operating system architecture microkernel for *** its safe,small,and flexible feature,micorkernel is becoming widely use in various *** it to education,will from different design architecture to make learner get deeper understanding of operating system *** is a real,second-generation microkernel whose source code is less than 15,000 lines,and it is freely available under the GNU General Public *** this paper,based on Fiasco,the microkernel operating system will be introduced especially in its kernel mechanism.

关键词： A Case Study of Microkernel for Education

来源：评论

学校读者我要写书评

暂无评论

BD-LZW picture compression algorithm for WSN system

BD-LZW picture compression algorithm for WSN system

引用

2008 3rd International Conference on Pervasive Computing and Applications, ICPCA08

作者： Jinlan, Zhan Qingguo, Zhou Shuwei, Bai Li, Cuihual Bin, Hu Li, Lian Department of Computer Science Video and Image Processing Lab Xiamen University China Engineering Research Center of Open Source Software and Real-time System Ministry of Education Department of Information Science and Engineering Lanzhou University China Department of Computing University of Central England United Kingdom

ISBN: (纸本)9781424420209

In the paper, a new parallel LZW-Like algorithm, bidirectory LZW algorithm (BD-LZW) will be interpreted The new algorithm can be used in data compression/decompression system which runs on multi-microprocessor system, such as CELL, which the algorithm will be implemented on. Different from the conventional parallel LZW algorithm with one input directory, BD-LZW algorithm allows two threads reading characters from two ends of string. By this method, the data can be partitioned for compression/decompression loading between two threads fairly and easily. The most important is the compression performance can be improved by the new algorithm. Comparing running time, it's lower 10% than conventional parallel LZW (P-LZW) algorithm when there are two threads running on CELL architecture. © 2008 IEEE.

关键词： Compression algorithms Wireless sensor networks Yarn Partitioning algorithms Image coding Data compression Video compression Image processing Computer science open source software

来源：评论

学校读者我要写书评

暂无评论

Is Free-software open-source ready for Medical Applications?

Is Free-Software Open-Source ready for Medical Applications?

引用

2008 IEEE International Symposium on IT in Medicine and Education(ITME 2008)

作者： Nicholas Mc Guire Distributed & Embedded System Lab(DSLab) Lanzhou UniversityChina Engineering Research Center of Open Source Software and Real-Time Systems Ministry of EducationLanzhou UniversityChina

While in the past years free-software has gained some acceptance in the domain of medical applications it has been mainly focused on quite typical IT-infrastructure cases -may that be billing systems,data warehousing,databases and content management systems a second area where free software has made prominent entrance has been in the area of imaging and high-volume data *** the area of medical devices,with rare exceptions,free-software is still quite underrepresented -in part due to acceptance but in part also due to plain technical ***/Linux,real-time and embedded variants and many free-software projected have made there way into medical applications -but is Free-software ready to cover the wide area of demands on medical platforms and there applications? The demands of medical platforms stretch more or less the entire range of computational capabilities: * battery powered -robust against power-failures * reliable in rough environment * compliant with safety regulations * robust and secure software platforms * standalone,networked all the way to clusters * extensibility for specialized hardware and software * from head-less to multithread graphical user-interfaces And all this for devices that sometimes only will be built in a few 10s or hundred devices? What advantages could free-software have here -what limitations are there -where do we still need to do *** software is not the answer to all problems in medical computing (or in any other area) -but it has a plethora of innovative and powerful solutions to *** will outline some of them along with some outstanding medical applications that have been built on free-software components.

关键词： Is Free-software open-source ready for Medical Applications

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：