检索结果-内蒙古大学图书馆

IEEE Symposium on computational Intelligence and Data Mining (CIDM)

作者： Ding Liu Minghu Jiang Xiaofang Yang School of Computer Science & Software Engineering Tianjin Polytechnic University Tianjin China School of Humanities and Social Sciences Lab. of Computational Linguistics Tsinghua University Beijing China

ISBN: (纸本)9781479945177

The article introduces quantum clustering inspired from the quantum mechanics and extended to text analysis. This novel method upgrades the nonparametric density estimation and, different from the latter, quantum clustering constructs the potential function to determine the cluster center instead of the Gaussian kernel function. The result of a comparative experiment proves the advantage of quantum clustering over the conventional Parzen-window, and the further trial on authorship identification illustrates the wide application scope of this novel method.

关键词： Clustering algorithms Quantum mechanics Equations Mathematical model Kernel Electric potential Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Message from the program co-chairs

Proceedings - Fifth International Conference on Grid and Coo...

引用

Proceedings - Fifth International Conference on Grid and Cooperative Computing, GCC 2006 2006年 12-12页

作者： Xiao, Wong Buyya, Rajkumar Liu, Yunhao National Laboratory for Parallel and Distributed Processing Changsha China GRIDS Lab. Dept. of Computer Science and Software Engineering University of Melbourne Australia Dept. of Computer Science Hong Kong University of Science and Technology Hong Kong Hong Kong

来源：评论

学校读者我要写书评

暂无评论

Message from the program co-chairs

Proceedings - Fifth International Conference on Grid and Coo...

引用

Proceedings - Fifth International Conference on Grid and Cooperative Computing, GCC 2006 - Workshops 2006年 12-12页

作者： Nong, Xiao Buyya, Rajkumar Liu, Yunhao National Laboratory for Parallel and Distributed Processing Changsha China GRIDS Lab. Dept. of Computer Science and Software Engineering University of Melbourne Australia Dept. of Computer Science Hong Kong University of Science and Technology Hong Kong Hong Kong

来源：评论

学校读者我要写书评

暂无评论

parallel GENETIC ALGORITHM ON PVM

引用

Wuhan University Journal of Natural sciences 1996年第Z1期1卷 605-610页

作者： Cuangming Lin Xin Yao(Department of Computer science, computational Intelligence GroupUniversity College, The University of New South Wales, ADFA)lain Macleod(Computer sciences lab.RSISE ANUCanberra, ACT, Australia 2600)Lishan Kang Yuping Chen(Institu Department of Computer Science Computational Intelligence Group University College The University of New South Wales ADFA Australia Computer Sciences Lab. RSISE ANU Canberra Australia Institute of Software Engineering Wuhan University Wuhan P.R.China

In this paper we describe an implementation of some kinds of parallel genetic algorithms on the PVM,parallel Virtual Machine, a portable parallel environment. We give details of a genetic algorithm running On many small subpopulations with an occasional identification and exchange of their useful information among subpopulations by means of message-passing functions of PVM. In this work, experiments were done to compare the parallel genetic algorithm and traditional sequential genetic algorithms.

关键词： parallel Genetic Algorithms parallel Virtual Machine(PVM) Island Model Cellular Model.

来源：评论

学校读者我要写书评

暂无评论

A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement

arXiv

引用

arXiv 2022年

作者： Yang, Yuting Huang, Pei Cao, Juan Li, Jintao Lin, Yun Dong, Jin Song Ma, Feifei Zhang, Jian Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing China National University of Singapore Singapore Laboratory of Parallel Software and Computational Science ISCAS Beijing China

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based adversarial attack to compromise NLP models and robustness enhancement technique. We first construct malicious prompts for each instance and generate adversarial examples via mask-and-filling under the effect of a malicious purpose. Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs). Furthermore, we design a prompt-based adversarial training method to improve the robustness of PLMs. As our training method does not actually generate adversarial samples, it can be applied to large-scale training sets efficiently. The experimental results show that our attack method can achieve a high attack success rate with more diverse, fluent and natural adversarial examples. In addition, our robustness enhancement method can significantly improve the robustness of models to resist adversarial attacks. Our work indicates that prompting paradigm has great potential in probing some fundamental flaws of PLMs and fine-tuning them for downstream tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Quantifying robustness to adversarial word substitutions

arXiv

引用

arXiv 2022年

作者： Yang, Yuting Huang, Pei Ma, Fei Fei Cao, Juan Zhang, Meishan Zhang, Jian Li, Jintao Key Lab Of Intelligent Information Processing Institute Of Computing Technology Chinese Academy Of Sciences Beijing100190 China University Of Chinese Academy Of Sciences Beijing100049 China Beijing100190 China Laboratory Of Parallel Software And Computational Science ISCAS Beijing100190 China China

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper and lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A kind of fuzzy constructive neural network and its application

A kind of fuzzy constructive neural network and its applicat...

引用

26th Chinese Control Conference, CCC 2007

作者： Tao, Wu Liwei, Chen Junjun, Mao Ling, Zhang State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing 210093 China Key Lab. IC and SP Anhui University Hefei 230039 China School of Mathematics and Computational Science Anhui University Hefei 230039 China

ISBN: (纸本)7900719229

Support vector machine (SVM) has been studied and applied extensively for its high accuracy, but it must construct SVM decision tree to classify sample sets with multiclass for it just be applicable for binary classification and solve a quadratic programming problem to gain optimal hyperplane either in sample spaces or in feature spaces;Alternative covering algorithm which designs neutral networks with spherical domains has the advantages of fast performance, some hard solving problems have been solved using this algorithm. In this paper, a new kind of structural learning algorithm which combining covering design algorithm, fuzzy set and SVM is put forward, instances show that this kind of networks has the virtue of both covering design algorithm and SVM.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Metallic liquid H3O in a thin-shell zone inside uranus and neptune

arXiv

引用

arXiv 2019年

作者： Huang, Peihao Liu, Hanyu Lv, Jian Li, Quan Long, Chunhong Wang, Yanchao Chen, Changfeng Ma, Yanming State Key Lab. of Superhard Mat. Innovation Center for Computational Physics Methods and Software College of Physics Jilin University Changchun130012 Beijing Computational Science Research Center Beijing100193 China Department of Physics and Astronomy University of Nevada Las VegasNE89154 United States International Center of Future Science Jilin University Changchun130012 China

The Solar System harbors deep unresolved mysteries despite centuries-long study. A highly intriguing case concerns anomalous non-dipolar and non-axisymmetric magnetic fields of Uranus and Neptune that have long eluded explanation by the prevailing theory. A thin-shell dynamo conjecture captures observed phenomena but leaves unexplained fundamental material basis and underlying mechanism. Here, we report the discovery of trihydrogen oxide (H3O) in metallic liquid state stabilized at extreme pressure and temperature conditions inside these icy planets. Calculated stability pressure field compared to known pressure-radius relation for Uranus and Neptune places metallic liquid H3O in a thin-shell zone near planetary cores. These findings from accurate quantum mechanical calculations rationalize the empirically conjectured thin-shell dynamo model and establish key physical benchmarks that are essential to elucidating the enigmatic magnetic-field anomaly of Uranus and Neptune, resolving a major mystery in planetary science. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Hardware/software co-design for high performance computing: Challenges and opportunities

Hardware/software co-design for high performance computing: ...

引用

作者： Hu, X. Sharon Murphy, Richard C. Dosanjh, Sudip Olukotun, Kunle Poole, Stephen Department of Computer Science and Engineering University of Notre Dame Notre Dame IN United States Scalable Computer Architecture Department Sandia National Laboratories Albuquerque NM United States Computer and Software Systems Department Sandia National Laboratories Albuquerque NM United States Department of Electrical Engineering Stanford University Stanford CA United States Computational Sciences Division Oak Ridge National Lab. Oak Ridge TN United States

ISBN: (纸本)9781605589053

This special session aims to introduce to the hardware/software codesign community challenges and opportunities in designing high performance computing (HPC) systems. Though embedded system design and HPC system design have traditionally been considered as two separate areas of research, they in fact share quite some common features, especially as CMOS devices continue along their scaling trends and the HPC community hits hard power and energy limits. Understanding the similarities and differences between the design practices adopted in the two areas will help bridge the two communities and lead to design tool developments benefiting both communities. © 2010 ACM.

关键词： Hardware-software codesign

来源：评论

学校读者我要写书评

暂无评论

Research on Simulation Technology Application on Higher Education for Deaf/hard-of-hearing Students in China

Research on Simulation Technology Application on Higher Educ...

引用

2014 3rd International Conference on science and Social Research

作者： Dengfeng Yao Zhili Liu Junxia Yan Yunfeng Qiu Beijing Key Laboratory of Information Service Engineering Beijing Union University Lab. of Computational Linguistics School of HumanitiesTsinghua University Special Education College Beijing Union University College of Computer Wuhan Vocational College of Software and Engineering Foreign Language College Jing Chu University of Science and Technology

In teaching of computer language, how can we improve their hearing of hearing-impaired students featured with special physiological characteristics and reduce the inconvenience and obstacles caused during teaching knowledge in the most effective way? In this research, we have applied simulation technology and developed the teaching simulation platform for them, and it is practically demonstrated in the hearing-impaired students in higher education and the application of research result that the system works well, with intuitive, efficient, and other characteristics, a strong promotion of the college teaching model changes, the language learning, education teaching and research referred.

关键词： robot simulation deaf/hard-of-hearing students educational technology

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

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

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：