检索结果-内蒙古大学图书馆

International Conference on Neural Information Processing

作者： A. Harati M.N. Ahmadabadi School of Intelligent Systems Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence & AI and Robotics Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

In multiagent reinforcement learning, inter-agent credit assignment is a fundamental problem, since a single scalar reinforcement signal is the only reliable feedback that teams of learning agents receive. This problem is more critical in groups of independent learners with a joint task. In this research, it is assumed that a critic agent receives the environment feedback and assigns a proper credit to each agent using some measures. Three of such measures for a team of cooperative agents with a parallel and AND-type task are introduced. These measures somehow compare the agents' knowledge. One of these criteria, called normal expertness, is a non-relative measure while two other ones (certainty and relative normal expertness) are relative measure. It is experimentally shown that relative measures work better as they contain more information for the critic agent.

关键词： Feedback intelligent agent intelligent robots Process control control systems intelligent control Artificial intelligence Robot kinematics Physics computing Reliability engineering

来源：评论

学校读者我要写书评

暂无评论

ROBUST CONGESTION control IN HIGH SPEED COMMUNICATION NETWORKS: A MODEL PREDICTIVE control APPROACH

引用

IFAC Proceedings Volumes 2002年第1期35卷 103-108页

作者： Hua O. Wang Yongru Gu Huajing Fang Laboratory for Intelligent and Nonlinear Control (LINC) Department of Electrical and Computer Engineering Duke University Durham NC 27708-0291 USA Center for Nonlinear and Complex Systems Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

In this paper, the design of explicit rate-based congestion control in high speed communication networks is considered. At a bottleneck node, there are multiple best-effort sources competing with other high priority cross traffic sources. The goal of congestion control is to achieve high link utilization, low packet loss, low delay, and fairness among the best-effort sources. In this paper, the high priority traffic is described by an autoregressive integrated moving average (ARIMA) process. To deal with the propagation delays associated with the best-effort sources, model predictive control, particularly, generalized predictive control, techniques are proposed to solve the congestion problem here. It is demonstrated that the proposed controller performs well and is robust to delay uncertainties. In addition, in a multiple-nodes configuration, the controller provides max-min fairness.

关键词： Communication control applications Model-based control Predictive control Communication networks Time delay Robustness

来源：评论

学校读者我要写书评

暂无评论

Implementation of virtual factory using MMS companion standard

Implementation of virtual factory using MMS companion standa...

引用

IEEE International Workshop on Factory Communication systems (WFCS)

作者： Kwan-Joo Myoung Dong-Sung Kim Wook Hyun Kwon Engineering Research Center for Advanced Control Instrument Control Information Systems Laboratory School of Electrical Engineering and Computer Science Seoul National University Seoul South Korea

In this paper, a virtual factory using the manufacturing message specification (MMS) companion standard is implemented. The MMS companion standard (9506-3/spl sim/9506-7) and virtual machines are designed and implemented for robot, numerical controller (NC), programmable logic controller (PLC), and process control (PC). Finally, the MMS Internet monitoring system (MIMS) is developed for the testing system.

关键词： Production facilities Virtual manufacturing TCPIP Programmable control Virtual machining Condition monitoring Virtual machine monitors Manufacturing automation computer integrated manufacturing control systems

来源：评论

学校读者我要写书评

暂无评论

Entire region filling in indoor environments using neural networks

Entire region filling in indoor environments using neural ne...

引用

World Congress on intelligent control and Automation (WCICA)

作者： Chaomin Luo S.X. Yang M. Meng Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph Canada Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

Entire region filling is a special type of robot path planning strategy that requires the mobile robot to cover every part of the whole workspace, which has many applications such as cleaning robots, vacuum cleaners, painter robots, land mine detectors, lawn mowers, and window cleaners. In this paper, a novel biologically inspired neural network approach is proposed for entire region filling with obstacle avoidance of a mobile cleaning robot in a nonstationary environment. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation or an additive equation derived from Hodgkin and Huxley's (1952) membrane equation. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The robot path is autonomously generated from the dynamic activity landscape of the neural network and the previous robot location. The proposed model algorithm is computationally efficient. It can deal with an unstructured environment with irregular obstacles. The effectiveness of the proposed model is demonstrated by simulation results.

关键词： Filling Indoor environments Neural networks Mobile robots Equations Cleaning Landmine detection Neurons Computational modeling Path planning

来源：评论

学校读者我要写书评

暂无评论

Cooperative Q-learning with heterogeneity in actions

Cooperative Q-learning with heterogeneity in actions

引用

IEEE International Conference on systems, Man and Cybernetics

作者： S.M. Reza MirFattah M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Cooperation in learning improves the speed of convergence and the quality of learning. Special care is needed when heterogeneous agents cooperate in learning. It is discussed that, cooperation in learning may cause the learning process to diverge if heterogeneity is not handled properly. In this paper, it is assumed that two heterogeneous Q-learning agents cooperate to learn. The heterogeneity is assumed in their action order (and not in their action set). A Q-learning-based method is introduced for the agents to learn the mapping among their actions. It is shown that, the agents are able to learn this mapping while cooperating in learning. Some simulation results are reported to show the effectiveness of the proposed method.

关键词： intelligent agent intelligent robots Humans Telecommunication control Artificial intelligence Laboratories intelligent systems Physics Mathematics Convergence

来源：评论

学校读者我要写书评

暂无评论

A new approach to credit assignment in a team of cooperative Q-learning agents

A new approach to credit assignment in a team of cooperative...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： A. Harati M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of all agents' actions on the team qualification. But, in many cases, the role of each team member in the group performance is not known. In order to distribute a common credit among the agents, a suitable criterion must be provided to estimate the role of each agent in the team performance and to judge if an agent has done a wrong action. In this paper two such criteria, named certainty and expertness, for a team of agents with parallel tasks are introduced. In addition, two methods for reinforcing the agents based on the proposed measures are provided. Some simulation results are also reported to show the effectiveness of the proposed measures and methods.

关键词： intelligent agent Learning systems Multiagent systems intelligent sensors Artificial intelligence Laboratories intelligent systems intelligent robots Physics Mathematics

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

Statistical approximation learning of discontinuous functions using simultaneous recurrent neural networks

Statistical approximation learning of discontinuous function...

引用

IEEE International Symposium on intelligent control (ISIC)

作者： M. Sakai N. Homma M.M. Gupta K. Abe Department of Computer and Mathematical Sciences Graduate School of Information Sciences University of Tohoku Sendai Japan Department of Radiological Technology College of Medical Sciences University of Tohoku Sendai Japan Intelligent Systems Research Laboratory College of Engineering University of Saskatchewan Saskatoon SAS Canada Department of Electrical and Communication Engineering Graduate School of Engineering University of Tohoku Sendai Japan

In this paper, we develop an architecture for a novel type of neural network which is known as simultaneous recurrent neural networks (SRNNs). Using this novel neural architecture, we propose a statistical approximation learning (SAL) method. The SRNNs have the capability to approximate non-smooth functions which cannot be approximated by using conventional multilayer perceptrons. However, most of the learning methods for the SRNNs are computationally expensive due to their inherent recursive calculations. To solve this problem, as an approximation learning method, the SAL method is proposed by using a statistical relation between the time-series of the network outputs and the network configuration parameters. Simulation results show that SRNNs trained by the proposed SAL method can learn a strongly nonlinear function efficiently within a practical computation time.

关键词： Recurrent neural networks Biological neural networks Neural networks Learning systems Educational institutions Biomedical engineering Multilayer perceptrons Computational modeling Multi-layer neural network Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Constructing a fuzzy rule-based system using the ILFN network and Genetic Algorithm.

引用

International journal of neural systems 2001年第5期11卷 427-443页

作者： Yen, G.G. Meesad, P. Intelligent Systems and Control Laboratory School of Electrical and Computer Engineering Oklahoma State University Stillwater 74078 OK United States

In this paper, a method for automatic construction of a fuzzy rule-based system from numerical data using the Incremental Learning Fuzzy Neural (ILFN) network and the Genetic Algorithm is presented. The ILFN network was developed for pattern classification applications. The ILFN network, which employed fuzzy sets and neural network theory, equips with a fast, one-pass, on-line, and incremental learning algorithm. After trained, the ILFN network stored numerical knowledge in hidden units, which can then be directly interpreted into if then rule bases. However, the rules extracted from the ILFN network are not in an optimized fuzzy linguistic form. In this paper, a knowledge base for fuzzy expert system is extracted from the hidden units of the ILFN classifier. A genetic algorithm is then invoked, in an iterative manner, to reduce number of rules and select only discriminate features from input patterns needed to provide a fuzzy rule-based system. Three computer simulations using a simulated 2-D 3-class data, the well-known Fisher's Iris data set, and the Wisconsin breast cancer data set were performed. The fuzzy rule-based system derived from the proposed method achieved 100% and 97.33% correct classification on the 75 patterns for training set and 75 patterns for test set, respectively. For the Wisconsin breast cancer data set, using 400 patterns for training and 299 patterns for testing, the derived fuzzy rule-based system achieved 99.5% and 98.33% correct classification on the training set and the test set, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Specification and Modeling of Network Resources in Dynamic, Distributed Real-time System 14

Specification and Modeling of Network Resources in Dynamic, ...

引用

14th International Conference on Parallel and Distributed Computing systems, PDCS 2001

作者： Tong, Lu Bruggeman, Carl Tjaden, Brett Chen, Hong Welch, Lonnie R. Laboratory for Intelligent Real-time Secure Systems School of Electrical Engineering and Computer Science Ohio University AthensOH45701 United States

ISBN: (纸本)9781618395740

This paper presents a system model and specification language for network resource management in dynamic, distributed real-time systems. The model is used to define techniques for QoS (quality-of-service) monitoring, QoS diagnosis, and schedulability analysis of network resources. Preliminary experimental results show the effectiveness of the extension for specification of realtime network resources, detection and diagnosis of network resources bottlenecks, and restoration of acceptable QoS via reallocation of distributed computer and network resources. © (2001) by the International Society for computers and Their Applications All rights reserved.

关键词： Specification languages

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：