Emergence is an important and promising scientific topic today because it offers benefits that can not be achieved by classic means. But it is often challenging to control emergence and to find correct local rules that create desired global behavior. It especially becomes difficult if the search space representing the problem that has to be optimized is not continuous/linear. One solution to that problem is evolution. This paper shows that the use of Genetic Algorithms is feasible for such problems by the example of the Creatures' Exploration Problem in which agents shall visit all non-blocked cells in a grid. Different amounts of agents and states per agent are evolved and statistically compared. It shows that neither a single extension of agent capabilities nor sole increase of agent numbers provides the best performance. The results hint that a mixture of both should be used instead.
{"title":"Evaluating the evolvability of emergent agents with different numbers of states","authors":"M. Komann, D. Fey","doi":"10.1145/1569901.1570155","DOIUrl":"https://doi.org/10.1145/1569901.1570155","url":null,"abstract":"Emergence is an important and promising scientific topic today because it offers benefits that can not be achieved by classic means. But it is often challenging to control emergence and to find correct local rules that create desired global behavior. It especially becomes difficult if the search space representing the problem that has to be optimized is not continuous/linear. One solution to that problem is evolution. This paper shows that the use of Genetic Algorithms is feasible for such problems by the example of the Creatures' Exploration Problem in which agents shall visit all non-blocked cells in a grid. Different amounts of agents and states per agent are evolved and statistically compared. It shows that neither a single extension of agent capabilities nor sole increase of agent numbers provides the best performance. The results hint that a mixture of both should be used instead.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134193341","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}
Geometric Particle Swarm Optimization (GPSO) is a recently introduced formal generalization of traditional Particle Swarm Optimization (PSO) that applies naturally to both continuous and combinatorial spaces. Differential Evolution (DE) is similar to PSO but it uses different equations governing the motion of the particles. This paper generalizes the DE algorithm to combinatorial search spaces extending its geometric interpretation to these spaces, analogously as what was done for the traditional PSO algorithm. Using this formal algorithm, Geometric Differential Evolution (GDE), we formally derive the specific GDE for the Hamming space associated with binary strings and present experimental results on a standard benchmark of problems.
{"title":"Geometric differential evolution","authors":"A. Moraglio, J. Togelius","doi":"10.1145/1569901.1570130","DOIUrl":"https://doi.org/10.1145/1569901.1570130","url":null,"abstract":"Geometric Particle Swarm Optimization (GPSO) is a recently introduced formal generalization of traditional Particle Swarm Optimization (PSO) that applies naturally to both continuous and combinatorial spaces. Differential Evolution (DE) is similar to PSO but it uses different equations governing the motion of the particles. This paper generalizes the DE algorithm to combinatorial search spaces extending its geometric interpretation to these spaces, analogously as what was done for the traditional PSO algorithm. Using this formal algorithm, Geometric Differential Evolution (GDE), we formally derive the specific GDE for the Hamming space associated with binary strings and present experimental results on a standard benchmark of problems.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134285407","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}
Inspired by the principle of gene transposon proposed by Barbara McClintock, a new immune computing algorithm for clustering multi-class data sets named as Gene Transposition based Clone Selection Algorithm (GTCSA) is proposed in this paper, The proposed algorithm does not require a prior knowledge of the numbers of clustering; an improved variant of the clonal selection algorithm has been used to determine the number of clusters as well as to refine the cluster center. a novel operator called antibody transposon is introduced to the framework of clonal selection algorithm which can realize to find the optimal number of cluster automatically. The proposed method has been extensively compared with Variable-string-length Genetic Algorithm(VGA)based clustering techniques over a test suit of several real life data sets and synthetic data sets. The results of experiments indicate the superiority of the GTCSA over VGA on stability and convergence rate, when clustering multi-class data sets.
{"title":"Gene transposon based clonal selection algorithm for clustering","authors":"Ruochen Liu, Zhengchun Sheng, L. Jiao","doi":"10.1145/1569901.1570069","DOIUrl":"https://doi.org/10.1145/1569901.1570069","url":null,"abstract":"Inspired by the principle of gene transposon proposed by Barbara McClintock, a new immune computing algorithm for clustering multi-class data sets named as Gene Transposition based Clone Selection Algorithm (GTCSA) is proposed in this paper, The proposed algorithm does not require a prior knowledge of the numbers of clustering; an improved variant of the clonal selection algorithm has been used to determine the number of clusters as well as to refine the cluster center. a novel operator called antibody transposon is introduced to the framework of clonal selection algorithm which can realize to find the optimal number of cluster automatically. The proposed method has been extensively compared with Variable-string-length Genetic Algorithm(VGA)based clustering techniques over a test suit of several real life data sets and synthetic data sets. The results of experiments indicate the superiority of the GTCSA over VGA on stability and convergence rate, when clustering multi-class data sets.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131645035","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}
Particle Swarm Optimization (PSO) is a metaheuristic that has been successfully applied to linear and non-linear optimization problems in functions with discrete and continuous domains. This paper presents a new variation of this algorithm - called oscPSO - that improves the inherent search capacity of the original (canonical) version of the PSO algorithm. This version uses a deterministic local search method whose use depends on the movement patterns of the particles in each dimension of the problem. The method proposed was assessed by means of a set of complex test functions, and the performance of this version was compared with that of the original version of the PSO algorithm. In all cases, the oscPSO variation equaled or surpassed the performance of the canonical version of the algorithm.
{"title":"Particle swarm optimization with oscillation control","authors":"Javier H. López, L. Lanzarini, A. D. Giusti","doi":"10.1145/1569901.1570141","DOIUrl":"https://doi.org/10.1145/1569901.1570141","url":null,"abstract":"Particle Swarm Optimization (PSO) is a metaheuristic that has been successfully applied to linear and non-linear optimization problems in functions with discrete and continuous domains. This paper presents a new variation of this algorithm - called oscPSO - that improves the inherent search capacity of the original (canonical) version of the PSO algorithm. This version uses a deterministic local search method whose use depends on the movement patterns of the particles in each dimension of the problem. The method proposed was assessed by means of a set of complex test functions, and the performance of this version was compared with that of the original version of the PSO algorithm. In all cases, the oscPSO variation equaled or surpassed the performance of the canonical version of the algorithm.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128941846","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}
We examine the convergence properties of genetic algorithms (GAs) in a wide variety of noisy environments where fitness perturbation can occur in any form for example, fitness functions can be concurrently perturbed by additive and multiplicative noise. We reveal the convergence properties of such GAs by constructing and analyzing a Markov chain that explicitly models the evolution of the algorithms. We compute the one-step transition probabilities of the chain and show that the chain has only one positive recurrent communication class. Based on this property, we establish a condition that is necessary and sufficient for GAs to eventually find a globally optimal solution with probability 1. We also identify a condition that is necessary and sufficient for GAs to eventually with probability 1 fail to find any globally optimal solution. Our analysis also shows that in all the noisy environments, the chain converges to stationarity: It has a unique stationary distribution that is also its steady-state distribution. We describe how this property and the one-step transition probabilities of the chain can be used to compute the exact probability that a GA is guaranteed to select a globally optimal solution upon completion of each iteration.
{"title":"Markov chain analysis of genetic algorithms in a wide variety of noisy environments","authors":"Takéhiko Nakama","doi":"10.1145/1569901.1570015","DOIUrl":"https://doi.org/10.1145/1569901.1570015","url":null,"abstract":"We examine the convergence properties of genetic algorithms (GAs) in a wide variety of noisy environments where fitness perturbation can occur in any form for example, fitness functions can be concurrently perturbed by additive and multiplicative noise. We reveal the convergence properties of such GAs by constructing and analyzing a Markov chain that explicitly models the evolution of the algorithms. We compute the one-step transition probabilities of the chain and show that the chain has only one positive recurrent communication class. Based on this property, we establish a condition that is necessary and sufficient for GAs to eventually find a globally optimal solution with probability 1. We also identify a condition that is necessary and sufficient for GAs to eventually with probability 1 fail to find any globally optimal solution. Our analysis also shows that in all the noisy environments, the chain converges to stationarity: It has a unique stationary distribution that is also its steady-state distribution. We describe how this property and the one-step transition probabilities of the chain can be used to compute the exact probability that a GA is guaranteed to select a globally optimal solution upon completion of each iteration.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130811321","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}
We present a set of single-core designed parallel SIMD Genetic Algorithm (GA) operators aimed at increasing computational speed of genetic algorithms. We use a discrete-valued chromosome representation. The explored operators include: single gene mutation, uniform crossover and a fitness evaluation function. We discuss their low-level hardware implementations on the Cell Processor. We use the Knapsack problem as a proof of concept, demonstrating performances of our operators. We measure the scalability in terms of generations per second. Using the architecture of the Cell Processor and a static population size of 648 individuals, we achieved 11.6 million generations per second on one Synergetic Processing Element (SPE) core for a problem size n = 8 and 9.5 million generations per second for a problem size n = 16. Generality for a problem size n multiple of 8 is also shown. Executing six independent concurrent GA runs, one per SPE core, allows for a rough overall estimate of 70 million generations per second and 57 million generations per second for problem sizes of n = 8 and n = 16 respectively.
{"title":"Design & Implementation of Real-time Parallel GA Operators on the IBM Cell Processor","authors":"P. Comte","doi":"10.1145/1569901.1596275","DOIUrl":"https://doi.org/10.1145/1569901.1596275","url":null,"abstract":"We present a set of single-core designed parallel SIMD Genetic Algorithm (GA) operators aimed at increasing computational speed of genetic algorithms. We use a discrete-valued chromosome representation. The explored operators include: single gene mutation, uniform crossover and a fitness evaluation function. We discuss their low-level hardware implementations on the Cell Processor. We use the Knapsack problem as a proof of concept, demonstrating performances of our operators. We measure the scalability in terms of generations per second. Using the architecture of the Cell Processor and a static population size of 648 individuals, we achieved 11.6 million generations per second on one Synergetic Processing Element (SPE) core for a problem size n = 8 and 9.5 million generations per second for a problem size n = 16. Generality for a problem size n multiple of 8 is also shown. Executing six independent concurrent GA runs, one per SPE core, allows for a rough overall estimate of 70 million generations per second and 57 million generations per second for problem sizes of n = 8 and n = 16 respectively.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131083441","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}
J. C. Ortíz-Bayliss, H. Terashima-Marín, P. Ross, Jorge Iván Fuentes-Rosado, Manuel Valenzuela-Rendón
This paper introduces a neuro-evolutionary approach to produce hyper-heuristics for the dynamic variable ordering for hard binary constraint satisfaction problems. The model uses a GA to evolve a population of neural networks architectures and parameters. For every cycle in the GA process, the new networks are trained using backpropagation. When the process is over, the best trained individual in the last population of neural networks represents the general hyper-heuristic.
{"title":"A neuro-evolutionary approach to produce general hyper-heuristics for the dynamic variable ordering in hard binary constraint satisfaction problems","authors":"J. C. Ortíz-Bayliss, H. Terashima-Marín, P. Ross, Jorge Iván Fuentes-Rosado, Manuel Valenzuela-Rendón","doi":"10.1145/1569901.1570174","DOIUrl":"https://doi.org/10.1145/1569901.1570174","url":null,"abstract":"This paper introduces a neuro-evolutionary approach to produce hyper-heuristics for the dynamic variable ordering for hard binary constraint satisfaction problems. The model uses a GA to evolve a population of neural networks architectures and parameters. For every cycle in the GA process, the new networks are trained using backpropagation. When the process is over, the best trained individual in the last population of neural networks represents the general hyper-heuristic.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133631566","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}
When evaluating a heuristic for a combinatorial problem, randomly generated instances of the problem may not provide a thorough exploration of the heuristic's performance, and it may not be obvious what kinds of instances challenge or confound the heuristic. An evolutionary algorithm can search a space of problem instances for cases that are heuristically difficult. Evaluation in such an EA requires an exact algorithm for the problem, which limits the sizes of the instances that can be explored, but the EA's (small) results can reveal misleading patterns or structures that can be replicated in larger instances. As an example, a genetic algorithm searches for instances of the quadratic knapsack problem that are difficult for a straightforward greedy heuristic. The GA identifies such instances, which in turn reveal patterns that mislead the heuristic.
{"title":"Evolving heuristically difficult instances of combinatorial problems","authors":"B. Julstrom","doi":"10.1145/1569901.1569941","DOIUrl":"https://doi.org/10.1145/1569901.1569941","url":null,"abstract":"When evaluating a heuristic for a combinatorial problem, randomly generated instances of the problem may not provide a thorough exploration of the heuristic's performance, and it may not be obvious what kinds of instances challenge or confound the heuristic. An evolutionary algorithm can search a space of problem instances for cases that are heuristically difficult. Evaluation in such an EA requires an exact algorithm for the problem, which limits the sizes of the instances that can be explored, but the EA's (small) results can reveal misleading patterns or structures that can be replicated in larger instances. As an example, a genetic algorithm searches for instances of the quadratic knapsack problem that are difficult for a straightforward greedy heuristic. The GA identifies such instances, which in turn reveal patterns that mislead the heuristic.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132007691","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}
A non-uniform cellular automata-based model is presented for the evolutionary development of digital circuits at the gate level. The main feature of this model is the modified local transition function of the cellular automaton in which a gate is associated with each rule of the transition function. A logic gate is generated by each cell when the cell determines its next state according to the appropriate rule. An evolutionary algorithm is utilized to design a non-uniform cellular automaton (its local transition function) for the development of a target circuit. In this paper, initial results will be presented that were obtained using the non-uniform cellular automata.
{"title":"Development of combinational circuits using non-uniform cellular automata: initial results","authors":"Michal Bidlo, Z. Vašíček","doi":"10.1145/1569901.1570192","DOIUrl":"https://doi.org/10.1145/1569901.1570192","url":null,"abstract":"A non-uniform cellular automata-based model is presented for the evolutionary development of digital circuits at the gate level. The main feature of this model is the modified local transition function of the cellular automaton in which a gate is associated with each rule of the transition function. A logic gate is generated by each cell when the cell determines its next state according to the appropriate rule. An evolutionary algorithm is utilized to design a non-uniform cellular automaton (its local transition function) for the development of a target circuit. In this paper, initial results will be presented that were obtained using the non-uniform cellular automata.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132394923","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}
The paper deals with optimization of collective communications on multistage interconnection networks (MINs). In the experimental work, unidirectional MINs like Omega, Butterfly and Clos are investigated. The study is completed by bidirectional binary, fat and full binary tree. To avoid link contentions and associated delays, collective communications are processed in synchronized steps. Minimum number of steps is sought for the given network topology, wormhole switching, minimum routing and given sets of sender and/or receiver nodes. Evolutionary algorithm proposed in this paper is able to design optimal schedules for broadcast and scatter collective communications. Acquired optimum schedules can simplify the consecutive writing high-performance communication routines for application-specific networks on chip, or for development of communication libraries in case of general-purpose multistage interconnection networks.
{"title":"Evolutionary optimization of multistage interconnection networks performance","authors":"J. Jaros","doi":"10.1145/1569901.1570107","DOIUrl":"https://doi.org/10.1145/1569901.1570107","url":null,"abstract":"The paper deals with optimization of collective communications on multistage interconnection networks (MINs). In the experimental work, unidirectional MINs like Omega, Butterfly and Clos are investigated. The study is completed by bidirectional binary, fat and full binary tree. To avoid link contentions and associated delays, collective communications are processed in synchronized steps. Minimum number of steps is sought for the given network topology, wormhole switching, minimum routing and given sets of sender and/or receiver nodes. Evolutionary algorithm proposed in this paper is able to design optimal schedules for broadcast and scatter collective communications. Acquired optimum schedules can simplify the consecutive writing high-performance communication routines for application-specific networks on chip, or for development of communication libraries in case of general-purpose multistage interconnection networks.","PeriodicalId":193093,"journal":{"name":"Proceedings of the 11th Annual conference on Genetic and evolutionary computation","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115457089","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：