检索结果-内蒙古大学图书馆

2011 11th International Conference on Intelligent Systems Design and Applications, ISDA'11

作者： García-Martínez, Carlos Rodriguez, Francisco J. Lozano, Manuel Dept. of Computing and Numerical Analysis University of Córdoba Córdoba Spain Dept. of Computer Sciences and Artificial Intelligence University of Granada Granada Spain

ISBN: (纸本)9781457716751

No Free Lunch theorems for optimisation state that there does not exist any algorithm better than any other one when averaged performances over the whole set of possible problems are considered. However, it has been recently suggested that algorithms might show performance differences when just the set of real-world problems is under study. In this work, we first assume that binary problems appearing in the literature are representative of the set of real-world binary problems. Then, we analyse the mean performance of several algorithms on subsets of this well-defined testbed, in particular, static combinatorial unconstrained single-objective single-player optimisation problems whose solutions can be directly encoded as arrays of binary variables. Our results provide empirical evidence that no free lunch theorems unlikely hold on this set of binary real-world problems. © 2011 IEEE.

关键词： binary optimisation empirical study no free lunch real-world problems

来源：评论

学校读者我要写书评

暂无评论

P system model optimisation by means of evolutionary based search algorithms 10

P system model optimisation by means of evolutionary based s...

引用

12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010

作者： García-Martínez, Carlos Lima, Claudio Twycross, Jamie Krasnogor, Natalio Dept. Computing and Numerical Analysis University of Córdoba 14071 Córdoba Spain Centre for Plant Integrative Biology University of Nottingham Sutton Bonington Campus Nottingham LE12 5RD United Kingdom ASAP Research Group School of Computer Science Jubilee Campus Nottingham NG8 1BB United States

ISBN: (纸本)9781450300728

Executable Biology, also called Algorithmic Systems Biology, uses rigorous concepts from computer science and mathematics to build computational models of biological entities. P systems are emerging as one of the key modelling frameworks within Executable Biology. In this paper, we address the continuous backward problem: given a P system model structure and a target phenotype (i.e. an intended biological behaviour), one is tasked with finding the (near) optimal parameters for the model that would make the P system model produce the target behaviour as closely as possible. We test several real-valued parameter optimisation algorithms on this problem. More specifically, using four different test cases of increasing complexity, we perform experiments with four evolutionary algorithms, and one variable neighbourhood search method combining three other evolutionary algorithms. The results show that, when there are few parameters to optimise, a genetic and two differential evolution based algorithms are robust optimisera attaining the best results. However, when the number of parameters increases, the variable neighbourhood search approach performs better. Copyright 2010 ACM.

关键词： Biology

来源：评论

学校读者我要写书评

暂无评论

A Continuous Variable Neighbourhood Search Based on Specialised EAs: Application to the Noiseless BBO-Benchmark 2009 09

A Continuous Variable Neighbourhood Search Based on Speciali...

引用

11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

作者： García-Martínez, Carlos Lozano, Manuel Dept. of Computing and Numerical Analysis University of Córdoba Córdoba14071 Spain University of Granada Granada18071 Spain

ISBN: (纸本)9781605583259

Variable Neighbourhood Search is a metaheuristic combining three components: generation, improvement, and shaking components. In this paper, we design a continuous Variable Neighbourhood Search algorithm based on three specialised Evolutionary Algorithms, which play the role of each aforementioned component: 1) an EA specialised in generating a good starting point as generation component, 2) an EA specialised in exploiting local information as improvement component, 3) and another EA specialised in providing local diversity as shaking component. Experiments are carried out on the noiseless Black-Box Optimisation Benchmark 2009 testbed. © 2009 ACM.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Immune network based ensembles 14

Immune network based ensembles

引用

14th European Symposium on Artificial Neural Networks, ESANN 2006

作者： García-Pedrajas, Nicolás Fyfe, Colin Dept. of Computing and Numerical Analysis University of Córdoba Spain Dept. of Computing University of Paisley United Kingdom

ISBN: (纸本)2930307064

This paper presents a new method for constructing ensembles of classifiers based on Immune Network Theory, one of the most interesting paradigms within the field of Artificial Immune Systems. Ensembles of classifiers are a very interesting alternative to single classifiers when facing difficult problems. In general, ensembles are able to achieve better performance in terms of learning and generalization error. We construct an Immune Network that constitutes an ensemble of classifiers. Using a neural network as base classifier we have compared the performance of this ensemble with five standard methods of ensemble construction. This comparison is made using 35 real-world classification problems from the UCI Machine Learning Repository. The results show a general advantage of the proposed model over the standard methods. © 2006 *** publication. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An OGSA-based accounting system for allocation enforcement across HPC centers 04

An OGSA-based accounting system for allocation enforcement a...

引用

ICSOC '04: Proceedings of the Second International Conference on Service Oriented computing

作者： Sandholm, Thomas Gardfjäll, Peter Elmroth, Erik Johnsson, Lennart Mulmo, Olle Dept. of Numerical Analysis and Computer Science PDC Royal Institute of Technology SE-100 44 Stockholm Sweden Dept. of Computing Science and HPC2N Umeå University SE-901 87 Umeå Sweden Dept. of Computer Science Texas Learning and Computation Center University of Houston Houston TX 77204 United States

ISBN: (纸本)1581138717

In this paper, we present an Open Grid Services Architecture (OGSA)-based decentralized allocation enforcement system, developed with an emphasis on a consistent data model and easy integration into existing scheduling, and workload management software at six independent high-performance computing centers forming a Grid known as SweGrid. The Swedish National Allocations Committee (SNAC) allocates resource quotas at these centers to research projects requiring substantial computer time. Our system, the SweGrid Accounting System (SGAS), addresses the need for soft real-time allocation enforcement on SweGrid for cross-domain job submission. The SGAS framework is based on state-of-the-art Web and Grid services technologies. The openness and ubiquity of Web services combined with the fine-grained resource control and cross-organizational security models of Grid services proved to be a perfect match for the SweGrid needs. Extensibility and customizability of policy implementations for the three different parties the system serves (the user, the resource manager, and the allocation authority) are key design goals. Another goal is end-to-end security and single sign-on, to allow resources - selected based on client policies - to act on behalf of the user when negotiating contracts with the bank in an environment where the six centers would continue to use their existing accounting policies and tools. We conclude this paper by showing the feasibility of SGAS, which is currently being deployed at the production sites, using simulations of reservation streams. The reservation streams are shaped using soft computing and policy-based algorithms. Copyright 2004 ACM.

关键词： Computer science

来源：评论

学校读者我要写书评

暂无评论

Introducing multi-objective optimization in cooperative coevolution of neural networks

引用

6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001

作者： García-Pedrajas, N. Sanz-Tapia, E. Ortiz-Boyer, D. Hervás-Martínez, C. Dept. of Computing and Numerical Analysis University of Cordoba Campus of Rabanales C2 Building 14071 Córdoba Spain

ISBN: (纸本)3540422358

This paper presents MONet (Multi-Objective coevolutive NET work), a cooperative revolutionary model for evolving artificial neural networks that introduces concepts taken from multi-objective optimization. This model is based on the idea of coevolving subnetworks that must cooperate to form a solution for a specific problem, instead of evolving complete networks. The fitness of each member of the subpopu- lations of subnetworks is evaluated using an evolutionary multi-objective optimization algorithm. This idea has not been used before in the area of evolutionary artificial neural networks. The use of a multiobjective evolutionary algorithm allows the definition of as many objectives as could be interesting for our problem and the optimization of these objectives in a natural way. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Why neuronal dynamics should control synaptic learning rules 01

Why neuronal dynamics should control synaptic learning rules

引用

Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic

作者： Jesper Tegnér Ádám Kepecs Stockholm Bioinformatics Center Dept. of Numerical Analysis & Computing Science Royal Institute for Technology Stockholm Sweden Volen Center for Complex Systems Brandeis University Waltham MA

Hebbian learning rules are generally formulated as static rules. Under changing condition (e.g. neoromodulation, input statistics) most rules are sensitive to parameters. In particular, recent work has focused on two different formulations of spike-timing-dependent plasticity rules. Additive STDP [1] is remarkably versatile but also very fragile, whereas multiplicative STDP [2, 3] is more robust but lacks attractive features such as synaptic competition and rate stabilization. Here we address the problem of robustness in the additive STDP rule. We derive an adaptive control scheme, where the learning function is under fast dynamic control by postsynaptic activity to stabilize learning under a variety of conditions. Such a control scheme can be implemented using known biophysical mechanisms of synapses. We show that this adaptive rule makes the additive STDP more robust. Finally, wo give an example how meta plasticity of the adaptive rule can be used to guide STDP into different type of learning regimes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hunting for functionally analogous genes 20th

引用

20th Conference on Foundations of Software Technology and Theoretical Computer Science, FST TCS 2000

作者： Hallett, Michael T. Lagergren, Jens McGill Centre for Bioinformatics McGill University Montreal Canada Stockholm Bioinformatics Center Dept. Of Numerical Analysis of Computing Science KTH Stockholm Sweden

ISBN: (纸本)3540414134

Evidence indicates that members of many gene families in the genome of an organism tend to have homologues both within their own genome and in the genomes of other organisms. Amongst these homologues, typically only one or a few per genome perform an analogous function in their genome. Finding subsets of these genes which show evidence of performing a common function is an important first step towards, for instance, the creation of phylogenetic trees, multiple sequence alignments and secondary structure predictions. Given a collection of taxa P = {P1, P2,..., Pk} where Pi contains genes {pi,1, pi,2,..., pi,ni}, we ask to choose one gene from each of the taxa Pisuch that these chosen vertices most agree. We define most agreeing in three distinct ways: most tree-like, pairwise closest, and pairwise most similar. We show these problems to be computationally hard from almost every angle via classical, parameterized and approximation complexity theory. However, on the positive side, we give randomized approximation algorithms following ideas from [GGR98] for the pairwise closest and pairwise most similar variants. © Springer-Verlag Berlin Heidelberg 2000.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Significance determination for the scale-space primal sketch by comparison of statistics of scale-space blob volumes computed from PET signals vs. residual noise

引用

NeuroImage 2000年第5 PART II期11.0卷 S493页

作者： Zagal, Juan Cristobal Björkman, Eva Lindeberg, Tony Roland, Per E. KTH Dept. of Numerical Analysis and Computing Science S-100 44 Stockholm Sweden Karolinska Institutet Dept. of Neuroscience S-171 77 Solna Sweden

来源：评论

学校读者我要写书评

暂无评论

Rationale and design of the European Computerized Human Brain Database System

Rationale and design of the European Computerized Human Brai...

引用

International Working Conference on Scientific and Statistical Database Management

作者： J. Fredriksson P. Roland P. Svensson Dept. of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Div. of Human Brain Research Dept. of Neuroscience Karolinska Institute Stockholm Dept. of Information Systems Technology Defence Research Establishment Stockholm

The European Computerized Human Brain Database (ECHBD) is an innovative approach to neuroscience, where state-of-the-art database technology has been utilised for building a system for meta-research. Meta-research here refers to research on 3D brain images, obtained from various neuroimaging techniques. The system is built on top of the RASDAMAN rasterdata manager and the object-oriented DBMS O/sub 2/. A client/server interface allows access to the database over the Internet. The system will be open for use by the ECHBD project partners in July 1999. The ECHBD system focuses on ease of use, featuring visual navigation and query specification. We discuss basic data management problems in experimental neuroscience and describe how the ECHBD system is designed to address these problems.

关键词： Humans Image databases Object oriented databases Neuroscience Buildings Brain Neuroimaging Web server Spatial databases Visual databases

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：