发布求助
文献互助 智能选刊 最新文献

The 2003 Congress on Evolutionary Computation, 2003. CEC '03.最新文献

筛选
英文 中文
Neuroevolution for reinforcement learning using evolution strategies 使用进化策略的强化学习神经进化
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299414
C. Igel
{"title":"Neuroevolution for reinforcement learning using evolution strategies","authors":"C. Igel","doi":"10.1109/CEC.2003.1299414","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299414","url":null,"abstract":"We apply the CMA-ES, an evolution strategy which efficiently adapts the covariance matrix of the mutation distribution, to the optimization of the weights of neural networks for solving reinforcement learning problems. It turns out that the topology of the networks considerably influences the time to find a suitable control strategy. Still, our results with fixed network topologies are significantly better than those reported for the best evolutionary method so far, which adapts both the weights and the structure of the networks.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115811677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 174
An evolutionary approach to behavioural-level synthesis 行为层面综合的进化方法
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299584
G. Grewal, Mike O'Cleirigh, M. Wineberg
{"title":"An evolutionary approach to behavioural-level synthesis","authors":"G. Grewal, Mike O'Cleirigh, M. Wineberg","doi":"10.1109/CEC.2003.1299584","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299584","url":null,"abstract":"This paper presents a novel approach to the concurrent solution of three high-level synthesis (HLS) problems and solves them in an integrated manner using hierarchical genetic algorithm (HGA). We focus on the core problems of HLS: scheduling, allocation, and binding. Scheduling consists of assigning of operations in an data-flow graph (DFG) to control steps or clock cycles. Allocation selects specific numbers and types of functional units from a hardware library to perform the operations specified in the DFG. Binding assigns constituent operations of the DFG to specific unit instances. A very general version of the problem is considered where functional units may perform different numbers of control steps. The HLS problems are solved by applying two genetic algorithms in a hierarchical manner. The first performs allocation, while the second performs scheduling and binding and serves as the fitness functions for the first. When compared to other, well-known techniques, our results show a reduction in time to obtain optimal solutions for standard benchmarks.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132044667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Comparison of sampling sizes for the co-evolution of cooperative agents 合作主体共同进化的抽样规模比较
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299622
G. Parker, H. Blumenthal
{"title":"Comparison of sampling sizes for the co-evolution of cooperative agents","authors":"G. Parker, H. Blumenthal","doi":"10.1109/CEC.2003.1299622","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299622","url":null,"abstract":"The evolution of heterogeneous team behaviour can be a very demanding task. In order to promote the greatest level of specialization team members should be evolved in separate populations. The greatest complication in the evolution of separate populations is finding suitable partners for evolution at trial time. If too few combinations are tested, the genetic algorithm loses its ability to recognize possible solutions and if too many combinations are tested the algorithm becomes too computationally expensive. In previous work a method of punctuated anytime learning was employed to test all combinations of possible partners at periodic generations to reduce the number of evaluations. In further works, it was found that by varying the number of combinations tested, the sample size, the GA could produce an accurate and even less computationally expensive solution. In this paper, we compare different sampling sizes to determine the most effective approach to finding the solution. We use a box pushing task to compare these different sampling sizes.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132492787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
Elitist multiobjective evolutionary algorithm for environmental/economic dispatch 环境/经济调度的精英多目标进化算法
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299792
R. King, H. Rughooputh
{"title":"Elitist multiobjective evolutionary algorithm for environmental/economic dispatch","authors":"R. King, H. Rughooputh","doi":"10.1109/CEC.2003.1299792","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299792","url":null,"abstract":"The environmental/economic dispatch problem is a multiobjective nonlinear optimization problem with constraints. Until recently, this problem has been addressed by considering economic and emission objectives separately or as a weighted sum of both objectives. Multiobjective evolutionary algorithms can find multiple Pareto-optimal solutions in one single run and this ability makes them attractive for solving problems with multiple and conflicting objectives. We use an elitist multiobjective evolutionary algorithm based on the nondominated sorting genetic algorithm-II (NSGA-II) for solving the environmental/economic dispatch problem. Elitism ensures that the population best solution does not deteriorate in the next generations. Simulation results are presented for a sample power system.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130101642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 135
Trying to evolve sorting networks in Echo 试图在Echo中改进分类网络
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299773
Lee K. Graham, F. Oppacher
{"title":"Trying to evolve sorting networks in Echo","authors":"Lee K. Graham, F. Oppacher","doi":"10.1109/CEC.2003.1299773","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299773","url":null,"abstract":"We describe an attempt to hybridize implicit and explicit fitness in ALife by augmenting the virtual organisms, called \"agents\", in John Holland's echo model to allow them to evolve 16-input sorting networks. The implementation of Echo is briefly described, as well as the method used to work sorting networks into the genetic material and rules of the system. The best, though imperfect, sorting network discovered is presented and compared to that of Hillis and to the best know network from Green.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131567170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A new multiobjective evolutionary algorithm: OMOEA 一种新的多目标进化算法:OMOEA
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299762
Sanyou Zeng, L. Ding, Yuping Chen, Lishan Kang
{"title":"A new multiobjective evolutionary algorithm: OMOEA","authors":"Sanyou Zeng, L. Ding, Yuping Chen, Lishan Kang","doi":"10.1109/CEC.2003.1299762","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299762","url":null,"abstract":"A new algorithm is proposed to solve constrained multiobjective problems. The constraints of the MOPs are taken account of in determining Pareto dominance. As a result, the feasibility of solutions is not an issue. At the same time, it takes advantage of both the orthogonal design method to search evenly, and the statistical optimal method to speed up the computation. The output of the technique is a large set of solutions with high precision and even distribution. Notably, for an engineering problem WATER, it finds the Pareto-optimal set, which was previously unknown.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131621935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Exploring regenerative mechanisms found in flatworms by artificial evolutionary techniques using genetic regulatory networks 利用遗传调控网络的人工进化技术探索扁形虫的再生机制
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299922
P. E. Hotz
{"title":"Exploring regenerative mechanisms found in flatworms by artificial evolutionary techniques using genetic regulatory networks","authors":"P. E. Hotz","doi":"10.1109/CEC.2003.1299922","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299922","url":null,"abstract":"The amazing self-repairing and self-assembling abilities of biological organisms are based on mechanisms, which once understood, have the far reaching promise to allow scientists to construct modular artefact mimicking these processes. In this line of research I investigated the possibility to evolve regenerating mechanisms in simulated, vermicular organisms. An artificial evolutionary system was developed able to evolve regenerative systems based on \"cells\" (modules). The performance of the evolutionary system relies on two mechanisms: firstly, genetic regulatory networks allowing to reduce the number of genetic parameters by informing whole groups of cells where they are and what to do and secondly, a specialized developmental mechanism, cell cleavage, which is able to specify in detail the cells after each cell division by distributing factors in the cells affecting their genes. It corresponds in many aspects to direct encoding scheme allowing to specify in detail the cells and it is possible to evolve recursive developmental schemes. The importance of cell lineage is its potential to get evolution started more easily, because information can be used specifically for one single cell.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130704640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 17
Genome-physics interaction as a new concept to reduce the number of genetic parameters in artificial evolution 基因组物理相互作用是人工进化中减少遗传参数数量的新概念
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299574
P. E. Hotz
{"title":"Genome-physics interaction as a new concept to reduce the number of genetic parameters in artificial evolution","authors":"P. E. Hotz","doi":"10.1109/CEC.2003.1299574","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299574","url":null,"abstract":"This paper reports on investigations on the possible advantage of the coupling between genomes and physics of cells in artificial evolution. The idea is simple: evolution can rely on physical processes during development allowing to produce shapes without need to specify how exactly this shaping has to be done. Evolving a minimal energy surface such as soap bubbles would need only the specification of the boundary values and a homogenous interaction pattern between the cells. This paper shows that it is possible to link a genetic regulatory network to physics during development, that a reduction of parameters is indeed possible and that the understanding of what is going on in such a system is relatively easy to gain.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130684910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 38
New concepts in evolutionary search for Boolean functions in cryptology 密码学中布尔函数进化搜索的新概念
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299939
W. Millan, Joanne Fuller, E. Dawson
{"title":"New concepts in evolutionary search for Boolean functions in cryptology","authors":"W. Millan, Joanne Fuller, E. Dawson","doi":"10.1109/CEC.2003.1299939","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299939","url":null,"abstract":"In symmetric cryptology (which is an essential part of modern computer security), the resistance to attacks depends critically on the nonlinearity properties of the Boolean functions describing cipher components like S-boxes. Some of the most effective methods known to generate functions that satisfy multiple criteria are based on evolutionary heuristics. In this paper, we improve on these algorithms by employing an adaptive strategy. Additionally, using recent improvements in the understanding of these combinatorial structures, we discover essential properties of the graph formed by affine equivalence classes of Boolean functions, which offers several advantages as a conceptual model for multiobjective seeking evolutionary heuristics. Finally, we propose the first major global cooperative effort to discover new bounds for cryptographic properties of Boolean functions.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130748376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 31
Evolutionary many-objective optimisation: an exploratory analysis 进化多目标优化:一种探索性分析
The 2003 Congress on Evolutionary Computation, 2003. CEC '03. Pub Date : 2003-12-08 DOI: 10.1109/CEC.2003.1299927
R. Purshouse, P. Fleming
{"title":"Evolutionary many-objective optimisation: an exploratory analysis","authors":"R. Purshouse, P. Fleming","doi":"10.1109/CEC.2003.1299927","DOIUrl":"https://doi.org/10.1109/CEC.2003.1299927","url":null,"abstract":"This inquiry explores the effectiveness of a class of modern evolutionary algorithms, represented by NSGA-II, for solving optimisation tasks with many conflicting objectives. Optimiser behaviour is assessed for a grid of recombination operator configurations. Performance maps are obtained for the dual aims of proximity to, and distribution across, the optimal trade-off surface. Classical settings for recombination are shown to be suitable for small numbers of objectives but correspond to very poor performance as the number of objectives is increased, even when large population sizes are used. Explanations for this behaviour are offered via the concepts of dominance resistance and active diversity promotion.","PeriodicalId":416243,"journal":{"name":"The 2003 Congress on Evolutionary Computation, 2003. CEC '03.","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132942484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 253
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书