R. E. Smith, Claudio Bonacine, P. Kearney, Torsten Eymann
Multi-agent software systems can be modeled as complex, dynamic systems in which agent adaptation and interaction occur continuously and concurrently. A genetics inspired view has agent adaptation occurring via the exchange of encoded agent characteristics (genes). An economics inspired view has agent adaptation driven by changes in prices and supply and demand. Interactions of economics and genetics models have a long history in evolutionary computation. This paper describes new work towards a synergistic combination of these views, in agent-based settings. The paper includes a re-statement of Holland's (1992) basic theories in an agent-based context, a discussion of different self-organization principles taken from economics, presentation of results from two agent systems that synergize economics and genetics models, and a discussion of future directions.
{"title":"Integrating economics and genetics models in information ecosystems","authors":"R. E. Smith, Claudio Bonacine, P. Kearney, Torsten Eymann","doi":"10.1109/CEC.2000.870747","DOIUrl":"https://doi.org/10.1109/CEC.2000.870747","url":null,"abstract":"Multi-agent software systems can be modeled as complex, dynamic systems in which agent adaptation and interaction occur continuously and concurrently. A genetics inspired view has agent adaptation occurring via the exchange of encoded agent characteristics (genes). An economics inspired view has agent adaptation driven by changes in prices and supply and demand. Interactions of economics and genetics models have a long history in evolutionary computation. This paper describes new work towards a synergistic combination of these views, in agent-based settings. The paper includes a re-statement of Holland's (1992) basic theories in an agent-based context, a discussion of different self-organization principles taken from economics, presentation of results from two agent systems that synergize economics and genetics models, and a discussion of future directions.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125874016","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 most difficult but realistic learning tasks are both noisy and computationally intensive. This paper investigates how, for a given solution representation, co-evolutionary learning can achieve the highest ability from the least computation time. Using a population of Backgammon strategies, this paper examines ways to make computational costs reasonable. With the same simple architecture Gerald Tasauro used for temporal difference learning to create the Backgammon strategy "Pubeval", co-evolutionary learning here creates a better player.
{"title":"Computationally intensive and noisy tasks: co-evolutionary learning and temporal difference learning on Backgammon","authors":"P. Darwen","doi":"10.1109/CEC.2000.870731","DOIUrl":"https://doi.org/10.1109/CEC.2000.870731","url":null,"abstract":"The most difficult but realistic learning tasks are both noisy and computationally intensive. This paper investigates how, for a given solution representation, co-evolutionary learning can achieve the highest ability from the least computation time. Using a population of Backgammon strategies, this paper examines ways to make computational costs reasonable. With the same simple architecture Gerald Tasauro used for temporal difference learning to create the Backgammon strategy \"Pubeval\", co-evolutionary learning here creates a better player.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126045885","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}
Testing is a key issue in the design and production of digital circuits and the adoption of built-in self test techniques is increasingly popular. This paper shows an application in the field of electronic CAD of the Selfish Gene algorithm, an evolutionary algorithm based on a recent interpretation of the Darwinian theory. A three-phase optimization algorithm is exploited for determining the structure of a built-in self test architecture that is able to achieve good fault coverage results with a reduced area overhead. Experimental results show that the attained fault coverage is substantially higher than what can be obtained by previously proposed methods with comparable area requirements.
{"title":"Exploiting the Selfish Gene algorithm for evolving hardware cellular automata","authors":"Fulvio Corno, M. Reorda, Giovanni Squillero","doi":"10.1109/CEC.2000.870816","DOIUrl":"https://doi.org/10.1109/CEC.2000.870816","url":null,"abstract":"Testing is a key issue in the design and production of digital circuits and the adoption of built-in self test techniques is increasingly popular. This paper shows an application in the field of electronic CAD of the Selfish Gene algorithm, an evolutionary algorithm based on a recent interpretation of the Darwinian theory. A three-phase optimization algorithm is exploited for determining the structure of a built-in self test architecture that is able to achieve good fault coverage results with a reduced area overhead. Experimental results show that the attained fault coverage is substantially higher than what can be obtained by previously proposed methods with comparable area requirements.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125052151","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 report a technique for using an evolutionary algorithm to select the parameters for a data-driven iterated function system. Such iterated function systems are typically driven with uniform random numbers to produce fractals. We instead drive the iterated function system with a biased source mimicking DNA with and without stop codons. An evolutionary algorithm is used to produce fractals that visually display the reading frame DNA. We perform a second set of experiments using the whole genome of mycobacterium tuberculosis in two different reading frames. The fractals located with our evolutionary algorithm correctly separate the DNA into in-frame and out-of-frame for the simulated data and the mycobacterium DNA. The fractals do not give dramatic visual cues to the differences for the mycobacterium data unless points associated with different members of the iterated function system are shaded. Close examination of the fractals yields insight into DNA structure.
{"title":"Iterated function system fractals for the detection and display of DNA reading frame","authors":"D. Ashlock, J. B. Golden","doi":"10.1109/CEC.2000.870779","DOIUrl":"https://doi.org/10.1109/CEC.2000.870779","url":null,"abstract":"We report a technique for using an evolutionary algorithm to select the parameters for a data-driven iterated function system. Such iterated function systems are typically driven with uniform random numbers to produce fractals. We instead drive the iterated function system with a biased source mimicking DNA with and without stop codons. An evolutionary algorithm is used to produce fractals that visually display the reading frame DNA. We perform a second set of experiments using the whole genome of mycobacterium tuberculosis in two different reading frames. The fractals located with our evolutionary algorithm correctly separate the DNA into in-frame and out-of-frame for the simulated data and the mycobacterium DNA. The fractals do not give dramatic visual cues to the differences for the mycobacterium data unless points associated with different members of the iterated function system are shaded. Close examination of the fractals yields insight into DNA structure.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130907054","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}
Mobile genetic elements, portions of DNA which are able to copy themselves elsewhere into the genome, have played a substantial role during evolution. One of the most prominent such elements is the LINE-1 retrotransposon, a section of DNA around 6,000 nucleotide bases in length, which is thought to account for about 15% of the current state of the human genome. The mechanism of LINE-1 insertion is rather poorly understood. However, achieving a good understanding of this process is fundamental to understanding natural evolution at the molecular level. We describe a first approach to use evolutionary computation to explore models for the LINE-1 insertion process. A range of findings from standard genome studies are able to suggest the basic parameters and structure of an insertion model. We use an evolutionary algorithm to explore a space of such models.
{"title":"Applying evolutionary computation to understanding the insertion behavior of LINE-1 retrotransposons in human DNA","authors":"A. Meade, D. Corne, R. Sibly","doi":"10.1109/CEC.2000.870717","DOIUrl":"https://doi.org/10.1109/CEC.2000.870717","url":null,"abstract":"Mobile genetic elements, portions of DNA which are able to copy themselves elsewhere into the genome, have played a substantial role during evolution. One of the most prominent such elements is the LINE-1 retrotransposon, a section of DNA around 6,000 nucleotide bases in length, which is thought to account for about 15% of the current state of the human genome. The mechanism of LINE-1 insertion is rather poorly understood. However, achieving a good understanding of this process is fundamental to understanding natural evolution at the molecular level. We describe a first approach to use evolutionary computation to explore models for the LINE-1 insertion process. A range of findings from standard genome studies are able to suggest the basic parameters and structure of an insertion model. We use an evolutionary algorithm to explore a space of such models.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130978920","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 describes ClaDia, a learning classifier system applied to the Wisconsin breast cancer data set, using a fuzzy representation of the rules, a median based fuzzy combination rule, and separate subpopulations for each class. The system achieves a classification rate of over 90%, for many sets of system parameter values.
{"title":"ClaDia: a fuzzy classifier system for disease diagnosis","authors":"D. Walter, C. K. Mohan","doi":"10.1109/CEC.2000.870821","DOIUrl":"https://doi.org/10.1109/CEC.2000.870821","url":null,"abstract":"The paper describes ClaDia, a learning classifier system applied to the Wisconsin breast cancer data set, using a fuzzy representation of the rules, a median based fuzzy combination rule, and separate subpopulations for each class. The system achieves a classification rate of over 90%, for many sets of system parameter values.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130451178","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}
This paper proposes a system of evolving analog circuits based on a variable length chromosome. Methods featured are the chromosome of a component list, the multi-stage evolution, and the pressure on the circuit size. A set of experiments are described to confirm the system's robustness, the scalability of a circuit, and the efficiency of time and the memory consumption. The first experiment shows the robustness supplied by the evolutionary method. The second one compares several types of chromosome implementation schemes. We also provide experiments to evaluate the multi-stage and scaling methods.
{"title":"Analog circuit design with a variable length chromosome","authors":"S. Ando, H. Iba","doi":"10.1109/CEC.2000.870754","DOIUrl":"https://doi.org/10.1109/CEC.2000.870754","url":null,"abstract":"This paper proposes a system of evolving analog circuits based on a variable length chromosome. Methods featured are the chromosome of a component list, the multi-stage evolution, and the pressure on the circuit size. A set of experiments are described to confirm the system's robustness, the scalability of a circuit, and the efficiency of time and the memory consumption. The first experiment shows the robustness supplied by the evolutionary method. The second one compares several types of chromosome implementation schemes. We also provide experiments to evaluate the multi-stage and scaling methods.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127959725","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}
Presents a genetic algorithm for the design of high-performance arithmetic circuits for evolvable hardware applications. A distinct feature of the algorithm is its ability to directly evolve and evaluate circuits in a hardware description language (HDL), within a novel environment termed the Virtual Chip. Because the Virtual Chip evolves circuit structures within a HDL, detailed simulation and analysis of each circuit is possible with any technology-specific component library. This feature allows accurate analysis of performance issues such as timing and area. The paper describes the genetic algorithm and the hardware evaluation environment, and provides results with a number of benchmark arithmetic circuits evolved under different performance-driven timing and area constraints. Our results reveal that the genetic algorithm is able to exploit the flexibility provided by a novel chromosome architecture, and utilise a combination of primitive gates and macro components from a component library in order to produce circuits which operate well within timing restrictions. The validity of our results are further supported by comparing the performance of functionally equivalent circuits generated using standard high-level design methodologies.
{"title":"A novel genetic algorithm for the automated design of performance driven digital circuits","authors":"B. Hounsell, T. Arslan","doi":"10.1109/CEC.2000.870353","DOIUrl":"https://doi.org/10.1109/CEC.2000.870353","url":null,"abstract":"Presents a genetic algorithm for the design of high-performance arithmetic circuits for evolvable hardware applications. A distinct feature of the algorithm is its ability to directly evolve and evaluate circuits in a hardware description language (HDL), within a novel environment termed the Virtual Chip. Because the Virtual Chip evolves circuit structures within a HDL, detailed simulation and analysis of each circuit is possible with any technology-specific component library. This feature allows accurate analysis of performance issues such as timing and area. The paper describes the genetic algorithm and the hardware evaluation environment, and provides results with a number of benchmark arithmetic circuits evolved under different performance-driven timing and area constraints. Our results reveal that the genetic algorithm is able to exploit the flexibility provided by a novel chromosome architecture, and utilise a combination of primitive gates and macro components from a component library in order to produce circuits which operate well within timing restrictions. The validity of our results are further supported by comparing the performance of functionally equivalent circuits generated using standard high-level design methodologies.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"2001 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128791960","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 cell formation problem is a classic manufacturing optimisation problem associated with the implementation of a cellular manufacturing system. A variety of hierarchical clustering procedures have been proposed for the solution of this problem. Essential for the operation of a clustering procedure is the determination of a form of similarity between the objects that are going to be grouped. The authors employ a genetic programming algorithm for the evolution of new similarity coefficients for the solution of simple cell formation problems. Evolved coefficients are tested against the well-known Jaccard's similarity coefficient on a large number of problems taken from the literature.
{"title":"Evolving similarity coefficients for the solution of cellular manufacturing problems","authors":"C. Dimopoulos, N. Mort","doi":"10.1109/CEC.2000.870355","DOIUrl":"https://doi.org/10.1109/CEC.2000.870355","url":null,"abstract":"The cell formation problem is a classic manufacturing optimisation problem associated with the implementation of a cellular manufacturing system. A variety of hierarchical clustering procedures have been proposed for the solution of this problem. Essential for the operation of a clustering procedure is the determination of a form of similarity between the objects that are going to be grouped. The authors employ a genetic programming algorithm for the evolution of new similarity coefficients for the solution of simple cell formation problems. Evolved coefficients are tested against the well-known Jaccard's similarity coefficient on a large number of problems taken from the literature.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125385688","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}
There have been many efforts to combine multilayer perceptrons (MLP) and radial basis function networks (RBFN). Among these works, circular backpropagation networks (CBPN) achieved both MLP and RBFN's properties by simply modifying MLP. In this paper, CBPN is extended to take all first and second-order terms of data as input. We show that the proposed network can represent not only MLP and RBFN but also ellipsoidal basis function networks (EBFN). Using Baldwin effect-based genetic algorithm, we develop an approach for optimizing this network.
{"title":"Second-order multilayer perceptrons and its optimization with genetic algorithms","authors":"M. Hwang, M. H. Kim, Jin-Young Choi","doi":"10.1109/CEC.2000.870360","DOIUrl":"https://doi.org/10.1109/CEC.2000.870360","url":null,"abstract":"There have been many efforts to combine multilayer perceptrons (MLP) and radial basis function networks (RBFN). Among these works, circular backpropagation networks (CBPN) achieved both MLP and RBFN's properties by simply modifying MLP. In this paper, CBPN is extended to take all first and second-order terms of data as input. We show that the proposed network can represent not only MLP and RBFN but also ellipsoidal basis function networks (EBFN). Using Baldwin effect-based genetic algorithm, we develop an approach for optimizing this network.","PeriodicalId":218136,"journal":{"name":"Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126876345","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：