检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： T. Gomi W. Pedrycz J.F. Peters S. Ramanna Applied AI Systems Inc. Kanata ONT Canada Computational Intelligence Laboratory Department of Electrical and Computer Engineering University of Manitoba Winnipeg MAN Canada Business Computing Department University of Winnipeg Winnipeg MAN Canada

The contribution of this paper is the introduction of an abstract sensor-actuator pair to the subsumption architecture of robots introduced by Brooks (1987). The perceiving side of this pair derives from Gibson's (1979) affordance, which is a form of grasping of situations involving perceived objects. This study is part of a new form of evolutionary robotics called cognitive robotics. It considers a new context for a classical form of learning, namely, habitation. The inspiration for the form of affordances described in this paper comes from Heidegger's (1982) notion of the convergence of the concurrent activities of building, dwelling and thinking. In some sense, building and dwelling are at the threshhold of thinking. A brief description of the form and functioning of abstract S-A pairs is given.

关键词： Robot sensing systems Cognitive robotics Actuators Buildings Humanoid robots Artificial intelligence computational intelligence Laboratories computer architecture Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Backpropagation of accuracy

Backpropagation of accuracy

引用

International Conference on Neural Networks

作者： M.Yu. Senashova A.N. Gorban D.C. Wunsch Krasnoyarsk State Univ. Russia Computing Center RAS RAS Russia Applied Computational Intelligence Laboratory Department of Electrical Engineering Texas Tech University Lubbock TX USA

We solve the problem: how to determine maximal allowable errors, possible for signals and parameters of each element of a network, proceeding from the condition that the vector of output signals of the network should ... 详细信息

关键词： Neural networks Neurons computer networks computational modeling Electronic mail Region 8 computational intelligence Laboratories Accuracy computer simulation

来源：评论

学校读者我要写书评

暂无评论

High order orthogonal tensor networks: information capacity and reliability

High order orthogonal tensor networks: information capacity ...

引用

International Conference on Neural Networks

作者： A.N. Gorban Y.M. Mirkes D.C. Wunsch Krasnoyarsk Computing Center RAS Computing Center RAS Krasnoyarsk State Technical University Russia Applied Computational Intelligence Laboratory Department of Electrical Engineering Texas Tech University Lubbock TX USA

Neural networks based on construction of orthogonal projectors in the tensor power of space of signals are described. A sharp estimate of their ultimate information capacity is obtained. The number of stored prototype patterns (prototypes) can many times exceed the number of neurons. A comparison with the error control codes is made.

关键词： Tensile stress Prototypes Vectors Neurons computer networks Power engineering computing Electronic mail Region 8 computational intelligence Laboratories

来源：评论

学校读者我要写书评

暂无评论

On Behaviors, Rational Interpolation, and the Lanczos Algorithm

引用

IFAC Proceedings Volumes 1996年第1期29卷 3957-3962页

作者： A.C. Antoulas E.J. Grimme D.C. Sorensen Department of Electrical and Computer Engineering Rice University Houston TX 77251-1892 USA Coordinated Science Laboratory University of Illinois at Urbana-Champaign Urbana IL 61801-2307 USA Department of Computational and Applied Mathematics Rice University Houston TX 77251-1892 USA

This paper explores the interconnections between two methods which can be used to obtain rational interpolants. The first method, the behavioral approach, constructs a generating system in the frequency domain which explains a given data set composed of trajectories. The second method, the rational Lanczos algorithm, can be used to construct a rational interpolant for the transfer function of a linear system defined by (potentially very high-order) state-space equations. This paper works to merge the theoretical attributes of the behavioral approach with the theoretical and computational properties of rational Lanczos. As a result, it lays the foundation for the computation of reduced-order, stabilizing controllers through rational interpolation.

关键词： linear systems behaviors rational interpolation Lanczos algorithm Krylov subspaces

来源：评论

学校读者我要写书评

暂无评论

Conservative thirty calendar day stock prediction using a probabilistic neural network

Conservative thirty calendar day stock prediction using a pr...

引用

Proceedings of the IEEE/IAFE computational intelligence for Financial engineering (CIFEr)

作者： H. Tan D.V. Prokhorov D.C. Wunsch Applied Computational Intelligence Laboratory Department of Electrical Engineering Texas Tech University Lubbock TX USA

Describes a system that predicts significant short-term price movement in a single stock utilizing conservative strategies. We use preprocessing techniques, then train a probabilistic neural network to predict only price gains large enough to create a significant profit opportunity. Our primary objective is to limit false predictions (known in the pattern recognition literature as false alarms). False alarms are more significant than missed opportunities, because false alarms acted upon lead to losses. We can achieve false alarm rates as low as 5.7% with the correct system design and parameterization.

关键词： Calendars Neural networks Costs Risk analysis Training data computational intelligence Laboratories Pattern recognition Information analysis Vehicles

来源：评论

学校读者我要写书评

暂无评论

Collaborative Fuzzy Linguistic Learning to Low-Resource and Robust Decision System Based on Bounded Rationality

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 1000年

作者： Chao Zhang Xiaochuan Li Arun Kumar Sangaiah Wentao Li Baoli Wang Feng Cao Xuekui Shangguan School of Computer and Information Technology Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Taiwan and Department of Electrical and Computer Engineering Lebanese American University Lebanon College of Artificial Intelligence Southwest University China and School of Computer and Information Technology Shanxi University China School of Mathematics and Information Technology Yuncheng University China Shanxi Information Industry Technology Research Institute Co. Ltd China

Low-resource languages are challenging to process intelligent decision systems due to limited data and resources. As an effective way of processing low-resource languages in intelligent decision systems, fuzzy linguistic approaches excel in transforming original uncertain linguistic information into highly structured data and learning valid decision rules between complex data structures. However, existing fuzzy linguistic methods may not fully capture realistic features of multi-attribute group decision-making (MAGDM), such as incomplete and hesitant linguistic expressions, stable information fusion, and bounded rationality of decision-makers (DMs). Therefore, it is necessary to develop a collaborative fuzzy language learning system based on bounded rationality, low-resource and robust decision-making. Specifically, we present a new multi-granularity (MG) group decision-making (GDM) scheme by using MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form) and PT (Prospect Theory) for incomplete hesitant fuzzy linguistic information systems (I-HFL-ISs), where MG GDM aims to discover knowledge from complex MAGDM problems with MG features. To achieve the above goal, we first introduce the concept of MG-I-HFL-ISs to represent incomplete, hesitant and imprecise linguistic evaluation information offered by multiple decision-makers (DMs). Then, we apply a valid transformation scheme to convert MG-I-HFL-ISs into MG-HFL-ISs, and use the MG probability rough set (PRS) to develop a series of MG-HFL-PRSs with the support of MULTIMOORA. Afterwards, an HFL MG GDM method is designed by integrating MULTIMOORA and PT for solving MAGDM problems with MG-I-HFL-ISs. The proposed method can effectively synthesize low-resource languages and mine useful decision-making knowledge. At last, a drug selection case and a simulated case are performed for showing the rationality of the designed HFL MG GDM scheme.

关键词： Fuzzy linguistic approach collaborative multiple feature fusion low-resource languages granular computing decision system

来源：评论

学校读者我要写书评

暂无评论

Advances in Neural Networks - ISNN 2006 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Jun Wang Zhang Yi Jacek M. Zurada Bao-Liang Lu Hujun Yin

ISBN: (数字)9783540344407

ISBN: (纸本)9783540344391

This book and its sister volumes constitute the Proceedings of the Third International Symposium on Neural Networks (ISNN 2006) held in Chengdu in southwestern China during May 28–31, 2006. After a successful ISNN 2004 in Dalian and ISNN 2005 in Chongqing, ISNN became a well-established series of conferences on neural computation in the region with growing popularity and improving quality. ISNN 2006 received 2472 submissions from authors in 43 countries and regions (mainland China, Hong Kong, Macao, Taiwan, South Korea, Japan, Singapore, Thailand, Malaysia, India, Pakistan, Iran, Qatar, Turkey, Greece, Romania, Lithuania, Slovakia, Poland, Finland, Norway, Sweden, Demark, Germany, France, Spain, Portugal, Belgium, Netherlands, UK, Ireland, Canada, USA, Mexico, Cuba, Venezuela, Brazil, Chile, Australia, New Zealand, South Africa, Nigeria, and Tunisia) across six continents (Asia, Europe, North America, South America, Africa, and Oceania). Based on rigorous reviews, 616 high-quality papers were selected for publication in the proceedings with the acceptance rate being less than 25%. The papers are organized in 27 cohesive sections covering all major topics of neural network research and development. In addition to the numerous contributed papers, ten distinguished scholars gave plenary speeches (Robert J. Marks II, Erkki Oja, Marios M. Polycarpou, Donald C. Wunsch II, Zongben Xu, and Bo Zhang) and tutorials (Walter J. Freeman, Derong Liu, Paul J. Werbos, and Jacek M. Zurada).

关键词： Artificial intelligence Computation by Abstract Devices computer Communication Networks Algorithm Analysis and Problem Complexity Discrete Mathematics in computer Science Pattern Recognition

来源：评论

学校读者我要写书评

暂无评论

Advances in Neural Networks - ISNN 2006 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Jun Wang Zhang Yi Jacek M. Zurada Bao-Liang Lu Hujun Yin

ISBN: (数字)9783540344834

ISBN: (纸本)9783540344827

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence and Soft Computing 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Leszek Rutkowski Rafał Scherer Ryszard Tadeusiewicz Lotfi A. Zadeh Jacek M. Zurada

来源：评论

学校读者我要写书评

暂无评论

Intelligent Computing and Optimization 1

引用

丛书名： Lecture Notes in Networks and Systems

1000年

作者： Pandian Vasant Mohammad Shamsul Arefin Vladimir Panchenko J. Joshua Thomas Elias Munapo Gerhard-Wilhelm Weber Roman Rodriguez-Aguilar

ISBN: (数字)9783031501517

ISBN: (纸本)9783031501500

The 6th edition of International Conference on Intelligent Computing and Optimization took place at G Hua Hin Resort & Mall on April 27–28, 2023, with tremendous support from the global research scholars across the planet. Objective is to celebrate “Research Novelty with Compassion and Wisdom” with researchers, scholars, experts, and investigators in Intelligent Computing and Optimization across the globe, to share knowledge, experience, and innovation—a marvelous opportunity for discourse and mutuality by novel research, invention, and creativity. This proceedings book of the 6th ICO’2023 is published by Springer Nature—Quality Label of Enlightenment.

关键词： computational intelligence Artificial intelligence

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：