检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： A.L. Magnus M.E. Oxley Intelligent Information Systems Air Force Research Laboratory Rome NY USA Department of Mathematics and Statistics Air Force Institute of Technology OH USA

A multilayer perceptron (MLP) represents a partial ordering over a feature set - an ordering based on the hyperplane arrangement implemented in the MLP's first hidden layer. This paper presents tools for manipulat... 详细信息

关键词： Multilayer perceptrons Nonhomogeneous media Training data intelligent systems information systems Laboratories Mathematics Statistics Helium Logic

来源：评论

学校读者我要写书评

暂无评论

Fusing and filtering arrogant classifiers

Fusing and filtering arrogant classifiers

引用

International Conference on information Fusion

作者： A.L. Magnus M.E. Oxley Intelligent Information Systems Air Force Research Laboratory Rome NY U.S.A Department of Mathematics and Statistics Air Force Institute of Technology OH U.S.A

Given a finite collection of classifiers trained on n-class data, one wishes to fuse the classifiers to form a new classifier with improved performance. Typically, the fusion is performed on the output level using logical ANDs and ORs. Sometimes classifiers are arrogant and will classify a feature vector without any prior experience (data) to justify their decision. The proposed fusion is based on the arrogance of the classifier and the location of the feature vector in respect to training data. Given a feature vector x, if any one of the classifiers is an expert on x then that classifier should dominate the fusion. If the classifiers are confused at x then the fusion rule should be defined in such a way to reflect this confusion. If the classifier is arrogant, then its results should not be considered and, thus, filtered out from the fusion process. We give this fusion rule based upon the metrics of veracity and experience.

关键词： Filtering Fuzzy logic intelligent systems information systems Laboratories Mathematics Statistics Fuses Image sensors Training data

来源：评论

学校读者我要写书评

暂无评论

A new model of the visual feedback coordinate transformation in humans based on disturbance noise and feedback error that accounts for time delays

A new model of the visual feedback coordinate transformation...

引用

IEEE International Workshop on intelligent Robots and systems (IROS)

作者： E. Oyama K.F. MacDorman T. Maeda S. Tachi A. Agah Science and Technology (AIST) National Institute for Advanced Industrial Science and Technology Tsukuba Ibaraki Japan Intelligent Robotics Laboratory Graduate School of Systems Engineering Wakayama University Wakayama Japan School of Engineering University of Tokyo Bunkyo Tokyo Japan Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

An essential factor in understanding the motor learning capability of humans, is the coordinate transformation learning of the visual feedback controller. Although a number of learning models for the visual feedback controller have been proposed, none has been able to establish a definitive approach. In our previous work, we have suggested a learning model that uses disturbance noise and the feedback error signal to learn the human visual feedback controller's coordinate transformation. However, the model does not fully consider the time delay in the visual feedback control loop. This paper presents a modified learning model taking into account the time delay and the convergence properties of the model. Numerical simulations are presented to illustrate the effectiveness of the proposed approach.

关键词： Humans Delay effects Adaptive control Error correction Biological system modeling Feedback control Convergence Kinematics intelligent robots Velocity control

来源：评论

学校读者我要写书评

暂无评论

A Grid Application for an Evaluation of Brain Function using Independent Component Analysis (ICA) 02

A Grid Application for an Evaluation of Brain Function using...

引用

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Y. Mizuno-Matsumoto S. Date T. Kaishima Y. Kadobayashi S. Shimojo Division of Interdisciplinary Image Analysis Department of Medical Robotics and Image Sciences Graduate School of Medicine Osaka University Osaka Japan Department of Information Systems Engineering Graduate School of Engineering Osaka University Osaka Japan Graduate School of Information Science Nara Institute of Science and Technology Nara Japan Cybermedia Center Osaka University Osaka Japan

ISBN: (纸本)9780769515823

For the effective and early diagnosis of brain diseases, we have developed an evaluation system for brain function using an Independent Component Analysis (ICA) method. This evaluation system benefits greatly from the newly emerged Grid. To embody a Grid environment, a Globus grid toolkit has been utilized as a building block. In this research we have distributed the computational workload for the ICA on a Globus based Grid environment composed of two Alpha cluster systems and a personal computer. In addition, in order to allow scientists and application developers to easily build the Grid-enabled system, we also have adopted a Grid-enabled-Message Passing Interface, called MPICH-G. An introduction of MPICH-G to the medical analysis system on a Grid environment makes it possible for a naïve user to realize rapid analysis without special knowledge of the Grid. Magnetoencephalography (MEG), a highly sophisticated medical technology, is used for the measurement of brain function. The proposed method has the ability to integrate various geographically distributed resources and to analyze functional brain data from MEG

关键词： Independent component analysis Magnetic analysis Medical diagnostic imaging Diseases Distributed computing Grid computing Microcomputers Application software Magnetoencephalography Data analysis

来源：评论

学校读者我要写书评

暂无评论

Matchmaking for structured objects 3rd

引用

3rd International Conference on Data Warehousing and Knowledge Discovery, DaWaK 2001

作者： Eiter, Thomas Veit, Daniel Müller, Jörg P. Schneider, Martin TU Vienna Institute of Information Systems Knowledge Based Systems Group Favoritenstrasse 11 ViennaA-1040 Austria Information Management and Systems Englerstrasse 14 KarlsruheD-76131 Germany Siemens AG Corporate Technology Intelligent Autonomous Systems Otto-Hahn-Ring 6 MunichD-81739 Germany

ISBN: (纸本)3540425535

A fundamental task in multi-agent systems is matchmaking, which is to retrieve and classify service descriptions of agents that (best) match a given service request. Several approaches to matchmaking have been proposed so far, which involve computation of distances between service offers and service requests that are both provided as aggregates of the same set of attributes which have atomic values. In this paper, we consider the problem of matchmaking in the setting where both service offers and requests are described in a richer language, which has complex types built from basic types using constructors such as sets, lists, or record aggregation. We investigate methods for computing distance values of complex objects, based on a generic combination of distance values of the object components, as well as domain-dependent distance functions. The methods have been implemented in Grappa, the Generic Request Architecture for Passive Provider Agents, which is a framework for developing open matchmaking facilities that can handle complex objects described in XML. Using Grappa, a large scale application has been built in the Human Resource Network project of the Office for Labor Exchange of the German government, in which job offerings have to be matched against a large database of unemployed persons and qualified candidates should be retrieved. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

STNS-R: a learning method for seamless transplantation from a virtual agent to a physical robot

STNS-R: a learning method for seamless transplantation from ...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： A. Ueno H. Soeda I. Takeda M. Kidode Graduate School of Information Science Nara Institute of Science and Technology Ikoma Nara Japan Intelligent Systems Research Division National Institute of Information Tokyo Japan

In this paper, we are concerned with the problem of how a physical robot can get an appropriate internal representation to its task and environment. Learning from experience is effective for the problem, but it is very time-consuming to learn a representation from the beginning in a real environment. On the other hand, the representation learned only in a simulated environment has the risk of not serving the purpose in a real environment because of the uncertainty in sensors, actuators, and the environment. In, order to have the best of both worlds, it is effective to transplant the learned state representation of a virtual agent to a physical robot. For this purpose., we improved our developed incremental learning architecture for use in the real environment and developed a new architecture, called STNS-R. In this architecture, inappropriate negative instances caused by uncertainties are found on the basis of the distribution of instances and removed in order to correct the distorted shapes of the states. The effectiveness of STNS-R is shown in the experimental results.

关键词： Learning systems intelligent robots Uncertainty Actuators Robot sensing systems Machine learning information science Appropriate technology intelligent systems intelligent agent

来源：评论

学校读者我要写书评

暂无评论

Agent architecture based on an interactive self-reflection classifier system

引用

Artificial Life and robotics 2001年第2期5卷 103-108页

作者： Takadama, Keiki Inoue, Hiroyasu Shimohara, Katsunori Okada, Michio Katai, Osamu Tokyo Institute of Technology Yokohama Japan ATR Human Information Science Laboratories Kyoto Japan Kyoto University Kyoto Japan ATR Intelligent Robotics and Communication Laboratories Kyoto Japan

This paper extends the learning classifier system (LCS) to introduce a mechanism for recognizing a current situation by determining a boundary between self and others, and investigates its capability through interaction with an agent. Intensive simulations for adapting to an interacting agent have revealed the following implications: (1) the proposed architecture adapts to an interacting agent more quickly and appropriately than the conventional LCS, and (2) our architecture keeps its adaptation to an interacting agent even when the agent changes its internal models before our architecture acquires it completely.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Behavior learning to predict using neural networks (NN): Ttowards a fast, cooperative and adversarial robot team (RoboCup)

Behavior learning to predict using neural networks (NN): Tto...

引用

International Workshop on Robot Motion and Control (RoMoCo)

作者： A. Chohra P. Scholl H.-U. Kobialka J. Hermes A. Bredenfeld GMD - German National Research Center for Information Technology Institute for Autonomous Intelligent Systems (AiS) Sankt Augustin Germany

To build a fast, cooperative and adversarial robot team (RoboCup), prediction behaviors became necessary. In the paper, a behavior learning method using neural networks (NN) is developed to enhance the behavior of GMD mobile robots. In fact, the suggested NN called NN-Prediction learns to predict successfulness of the elementary behavior "Kick" the ball towards the goal in order to act as consequence. The training is carried out by the supervised gradient back-propagation learning paradigm. This NN-Prediction has been specified on the Dual Dynamics Designer, to be thereafter implemented and tested on both the Dual Dynamics Simulator and GMD mobile robots, and analyzed on the Real-Time Trace Tool. NN-prediction demonstrated, during the 4/sup th/ World Championships RoboCup 2000, cooperative and adversarial behaviors especially face to situations where the successfulness of "Kick" is not guaranteed. Then, a discussion is given dealing with the suggested prediction behavior and how it relates to some other works.

关键词： Neural networks intelligent robots Artificial intelligence Cognitive science intelligent sensors intelligent systems Biological neural networks Mobile robots Learning systems Psychology

来源：评论

学校读者我要写书评

暂无评论

An architecture supporting loose and close cooperation of distributed autonomous systems

An architecture supporting loose and close cooperation of di...

引用

International Symposium on Object-Oriented Real-Time Distributed Computing

作者： M. Mock Institute for Autonomous intelligent Systems GMD-German National Research Center for Information Technology (GMD) Saint Augustine USA

ISBN: (纸本)0769510892

There is a general trend in designing distributed control systems to give an increasing amount of autonomy to the individual nodes of such systems. Autonomous nodes interact only loosely. But also, close cooperation under hard real-time constraints is required in certain situations. This paper analyzes approaches for structuring distributed control systems and presents an architecture integrating object-oriented frameworks, publisher/subscriber communication, and hard- and soft-real-time communication. For supporting mobile robots. Wireless communication is considered in particular.

关键词： Real time systems Distributed control Control systems robotics and automation Mobile communication Automatic control Service robots Robot kinematics intelligent robots Communication system control

来源：评论

学校读者我要写书评

暂无评论

Mechanisms for a reliable cooperation of vehicles

Mechanisms for a reliable cooperation of vehicles

引用

IEEE International Symposim on High Assurance systems Engineering

作者： E. Nett M. Gergeleit M. Mock Distributed Systems Institute IVS Otto von Guericke Universität Magdeburg Germany Institute for Autonomous intelligent Systems GMD-German National Research Center of Information Technology Germany

The final objective of the described project is to develop and implement techniques for a reliable cooperation of autonomous mobile systems that can be used for future traffic management systems. The approach relies on the ability of the systems to communicate among themselves in order to make efficient use of available shared resources (e.g. road space). In the context of automotives this means that computer-based driving assistants not only support humans in handling their own vehicles but also in interacting with the individual vehicles in the neighborhood The vision is an embedded, distributed traffic control system that is provided by the cooperation of the participating units, and thus is more robust and scalable than centralized approaches. Besides the 'obvious' requirements on high assurance computing in traffic control systems, the design and implementation of such systems require the ability of coordination while obeying the necessary real-time and safety constraints. This paper motivates the approach, presents an envisaged system architecture and sketches the design of the basic communication layers of this architecture that can fulfill the realtime and safety requirements. Finally, it introduces a lab-scale evaluation and demonstration scenario that proves the feasibility of the concepts.

关键词： Vehicle driving Traffic control Safety Computer architecture Remotely operated vehicles Project management Roads Context Automotive engineering Computer vision

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：