检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks, IJCNN 2005

作者： Holmstrom, Lars Santiago, Roberto Lendaris, George G. NW Computational Intelligence Laboratory Portland State University Portland OR 97201 Systems Science Ph.D. Program Department of Systems Science and Electrical and Computer Engineering

ISBN: (纸本)0780390482

Mathematical models are often used in system identification applications. The dynamics of most systems, however, change over time and the sources of these changes cannot always be directly determined or measured. To maintain model accuracy, it is desirable to design system identifiers that can adapt to these dynamical shifts. We use reinforcement learning to train an agent to recognize dynamical changes in a modeled system and to estimate new parameter values for the model. The subsequent actions of this agent are characterized as "moving" the parameterized model on an optimal trajectory in model parameter space. It is found that this method is capable of quickly and accurately discerning the correct parameter values. © 2005 IEEE.

关键词： Identification (control systems)

来源：评论

学校读者我要写书评

暂无评论

Book review The Internet in the Workplace , Patricia Wallace , Cambridge University Press , Cambridge, UK ( 2004 ) , 301 pp.

引用

Technological Forecasting and Social Change 2005年第6期72卷 753-755页

作者： Wayne Wakeland Systems Science Ph.D. Program Portland State University Portland OR 97207 USA

来源：评论

学校读者我要写书评

暂无评论

Reconstructability analysis as a tool for identifying gene-gene interactions in studies of human diseases

Reconstructability analysis as a tool for identifying gene-g...

引用

IEEE systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on systems, Man and Cybernetics

作者： Shervais, Stephen Zwick, Martin Kramer, Patricia College of Business and Public Administration Eastern Washington University Cheney WA 99004 Systems Science Ph.D. Program Portland State University Portland OR 97207 Department of Neurology Oregon Health Science University Portland OR 97239

There are a number of human diseases that are caused by the epistatic Interaction of multiple genes. detecting these interactions with standard statistical tools is difficult, because there may be an interaction effect, but minimal or no main effect. Reconstructability analysis uses Shannon's information theory to detect relationships between variables in categorical datasets. We apply reconstructability analysis to data generated by five different models of gene-gene interaction, with heritability levels from 0.053 to 0.008, using 200 controls and 200 cases. We find that even with heritability levels as low as 0.008, and with the inclusion of 50 non-associated genes in the data-set, we can identify the interacting gene pairs with an accuracy of 80% or better. © 2005 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Hamilton's rule applied to reciprocal altruism

Hamilton's rule applied to reciprocal altruism

引用

Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004

作者： Fletcher, Jeffrey A. Zwick, Martin Systems Science Ph.D. Program Portland State University Portland OR 97207

ISBN: (纸本)0780385152

Reciprocal altruism and inclusive fitness are generally considered alternative mechanisms by which cooperative, altruistic traits may evolve. Here we demonstrate that very general versions of Hamilton's inclusive fitness rule (developed by Queller) can be applied to traditional reciprocal altruism models such as the iterated Prisoner's dilemma. In this way we show that both mechanisms rely fundamentally on the same principle - the positive assortment of helping behaviors. We discuss barriers to this unified view, including phenotype/genotype differences and non-additive fitness (or utility) functions that are typical of reciprocal altruism models. We then demonstrate how Queller's versions of Hamilton's rule remove these obstacles.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

The Social Affordances of the Internet for Networked Individualism

引用

Journal of Computer-Mediated Communication 2006年第3期8卷

作者： Barry Wellman Anabel Quan-Haase Jeffrey Boase Wenhong Chen Keith Hampton Isabel díaz Kakuko Miyata In 1965 moved from his Bronx High School of Science slide rule to IBM cards and an 029 keypunch in the bowels of Harvard University. Since then he's been primarily interested in the interplay between large-scale social processes and how people use technology to be connected at work and in the community. His NetLab research network is trying to get a handle on how the Internet fits into everyday life. Wellman founded the International Network for Social Network Analysis in 1976. He is a recent Chair of the Community section of the American Sociological Association has been nominated for the Chair of the Communication and Information Technology section of the ASA the Virtual Community focus area leader for SIGGROUP/ACM and a Executive Cmmittee member of the Association for Internet Researchers. Wellman's (co)edited books are: Social Structures: A Network Approach (2d ed CSPI 2003) Networks in the Global Village (Westview Press 1999) and The Internet in Everyday Life (Blackwell Publishers 2002). Address:Centre for Urban & Community Studies University of Toronto 455 Spadina Avenue Toronto Canada M5S 2G8. Fax: +1-416-978-7162 Address:Centre for Urban & Community Studies University of Toronto 455 Spadina Avenue Toronto M5S 2G8 Canada. Address:Massachusetts Institute of Technology 77 Mass. Ave. Room 9-522 Cambridge MA 02139. Address:IN3 Av. Tibidabo 47 08035 Barcelona Spain. Phone: +*** Fax: +***. Address:Department of Sociology Meiji Gakuin University 1-2-37 Shirokanedai Minato-ku Tokyo 108-8636 JAPAN. Phone: +81-3-5421-5565 Fax: +81-3-5421-5697. Doctoral student at the Faculty of Information Studies University of Toronto. She has been a Fellow of the Knowledge Media Design Institute and the McLuhan Program in Culture and Technology. Her articles address the nature of Internet-related social change for social integration and information flow. Her articles have examined the implications of these changes for communities and her thesis focuses on organizations. University of Toronto doctoral

We review the evidence from a number of surveys in which our NetLab has been involved about the extent to which the Internet is transforming or enhancing community. The studies show that the Internet is used for connectivity locally as well as globally, although the nature of its use varies in different countries. Internet use is adding on to other forms of communication, rather than replacing them. Internet use is reinforcing the pre-existing turn to societies in the developed world that are organized around networked individualism rather than group or local solidarities. The result has important implications for civic involvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive critic learning with fuzzy utility

Adaptive critic learning with fuzzy utility

引用

NAFIPS 2004 - Annual Meeting of the North American Fuzzy Information Processing Society: Fuzzy Sets in the Heart of the Canadian Rockies

作者： Matzner, Shari A. Shannon, Thaddeus T. NW Computational Intelligence Lab. Systems Science Ph.D. Program Portland State University P.O. Box 751 Portland OR 97207 United States

Adaptive Critic methods, which approximate dynamic programming, have been used successfully for solving optimal control problems. The Adaptive Critic learning algorithm optimizes a secondary utility function that is the sum of the present and an future primary utility. The primary utility function measures the instantaneous cost incurred for the last action taken and the resulting state. The motivation for using a fuzzy primary utility function comes from the set of control problems for which there is only a qualitative definition of performance - for example, success or failure. Previous work in applying Adaptive Critic methods to this type of problem showed that a crisp definition of success resulted in solutions that met the control objective, but in an undesirable manner. An appropriate fuzzy utility function, on the other hand, is able to generate the optimal solution. Another motivation for incorporating fuzzy techniques into the utility function is to overcome measurement noise. Measurement noise has a significant adverse effect on the reliability and speed of Adaptive Critic learning;by incorporating fuzzy sets into the utility function, the effect of the noise can be mitigated.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Learning with binary-valued utility using derivative adaptive critic methods

Learning with binary-valued utility using derivative adaptiv...

引用

2004 IEEE International Joint Conference on Neural Networks - Proceedings

作者： Matzner, Shari A. Shannon, Thaddeus T. Lendaris, George G. NW Compl. Intelligence Lab Systems Science Ph.D. Program Portland State University P.O. Box 751 Portland OR 97207 United States

ISBN: (纸本)0780383591

Adaptive Critic methods for reinforcement learning are known to provide consistent solutions to optimal control problems, and are also considered plausible models for cognitive learning processes. This paper discusses binary reinforcement in the context of three Adaptive Critic methods: Heuristic dynamic programming (HdP), dual Heuristic programming (dHP), and Globalized dual Heuristic programming (GdHP). Binary reinforcement arises when the qualitative measure of success is simply "pass" or "fail". We implement binary reinforcement with Adaptive Critic methods for the pole-cart benchmark problem. Results demonstrate two qualitatively dissimilar classes of controllers: those that replicate the system stabilization achieved with quadratic utility, and those that merely succeed at not dropping the pole. It is found that the GdHP method is effective for learning an approximately optimal solution, with results comparable to those obtained via dHP that uses a more informative, quadratic utility function.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Hamilton's rule applied to reciprocal altruism

Hamilton's rule applied to reciprocal altruism

引用

Congress on Evolutionary Computation

作者： J.A. Fletcher M. Zwick Systems Science Ph.D. Program Portland State University Portland OR USA

Reciprocal altruism and inclusive fitness are generally considered alternative mechanisms by which cooperative, altruistic traits may evolve. Here we demonstrate that very general versions of Hamilton's inclusive fitness rule (developed by Queller) can be applied to traditional reciprocal altruism models such as the iterated prisoner's dilemma. In this way we show that both mechanisms rely fundamentally on the same principle - the positive assortment of helping behaviors. We discuss barriers to this unified view, including phenotype/genotype differences and nonadditive fitness (or utility) functions that are typical of reciprocal altruism models. We then demonstrate how Queller's versions of Hamilton's rule remove these obstacles.

关键词： Equations Genetics Frequency Productivity Yarn Predictive models Costs

来源：评论

学校读者我要写书评

暂无评论

A comparison of system dynamics and agent-based simulation applied to the study of cellular receptor dynamics

A comparison of system dynamics and agent-based simulation a...

引用

The Hawaii International Conference on System sciences, HICSS 2004

作者： Wakeland, Wayne W. Macovsky, Louis M. Gallaher, Edward J. Aktipis, C. Athena Systems Science Ph.D. Program Portland State University United States Dynamic BioSystems LLC Behav. Neurosci. Pharmacol./P. Oregon Health and Science University United States Department of Psychology University of Pennsylvania United States

Cellular receptor dynamics are often analyzed using differential equations, making system dynamics (Sd) a candidate methodology. In some cases it may be useful to model the phenomena at the biomolecular level, especially when concentrations and reaction probabilities are low and might lead to unexpected behavior modes. In such cases, agent-based simulation (ABS) may be useful. We show the application of both Sd and ABS to simulate non-equilibrium ligand-receptor dynamics over a broad range of concentrations, where the probability of interaction varies from low to very low. Both approaches offer much to the researcher and are complementary. We did not find a clear demarcation indicating when one paradigm or the other would be strongly preferred, although Sd is an obvious choice when studying systems at a high level of aggregation and abstraction, and ABS is well suited to studying phenomena at the level of individual receptors and molecules.

关键词： systems analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive critic learning with fuzzy utility

Adaptive critic learning with fuzzy utility

引用

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： S.A. Matzner T.T. Shannon NW Computational Intelligence Laboratory Systems Science Ph.D. Program Portland State University Portland OR USA

Adaptive critic methods, which approximate dynamic programming, have been used successfully for solving optimal control problems. The adaptive critic learning algorithm optimizes a secondary utility function that is the sum of the present and all future primary utility. The primary utility function measures the instantaneous cost incurred for the last action taken and the resulting state. The motivation for using a fuzzy primary utility function comes from the set of control problems for which there is only a qualitative definition of performance - for example, success or failure. Previous work in applying adaptive critic methods to this type of problem showed that a crisp definition of success resulted in solutions that met the control objective, but in an undesirable manner. An appropriate fuzzy utility function, on the other hand, is able to generate the optimal solution. Another motivation for incorporating fuzzy techniques into the utility function is to overcome measurement noise. Measurement noise has a significant adverse effect on the reliability and speed of adaptive critic learning; by incorporating fuzzy sets into the utility function, the effect of the noise can be mitigated.

关键词： dynamic programming Optimal control programmable control Adaptive control Cost function Control systems Computational intelligence Fuzzy sets Noise measurement Neural networks

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：