Results 21  30
of
73
Tightness Time for the Linkage Learning Genetic Algorithm
 Genetic and Evolutionary Computation  GECCO 2003
, 2003
"... This paper develops a model for tightness time, linkage learning time for a single building block, in the linkage learning genetic algorithm (LLGA). First, the existing models for both linkage learning mechanisms, linkage skew and linkage shift, are extended and investigated. Then, the tightness tim ..."
Abstract

Cited by 8 (3 self)
 Add to MetaCart
(Show Context)
This paper develops a model for tightness time, linkage learning time for a single building block, in the linkage learning genetic algorithm (LLGA). First, the existing models for both linkage learning mechanisms, linkage skew and linkage shift, are extended and investigated. Then, the tightness time model is derived and proposed based on the extended linkage learning mechanism models. Experimental results are also presented in this study to verify the extended models for linkage learning mechanisms and the proposed model for tightness time.
Efficient Cluster Optimization Using Extended Compact Genetic Algorithm With Seeded Population
 In Proceedings of the Optimization by Building and Using Probabilistic Models OBUPM Workshop at the Genetic and Evolutionary Computation Conference (GECCO2001 OBUPM
, 2001
"... This study presents an ecient atomic cluster optimization algorithm that utilizes a hybrid extended compact genetic algorithm along with an eciency enhancement technique called seeding. Empirical results indicate that the population size and total number of function evaluations scale up with ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
(Show Context)
This study presents an ecient atomic cluster optimization algorithm that utilizes a hybrid extended compact genetic algorithm along with an eciency enhancement technique called seeding. Empirical results indicate that the population size and total number of function evaluations scale up with the cluster size as O n 0:83 and O n 2:45 respectively. The results also indicate that the proposed algorithm is not only very reliable in predicting lowest energy structures, but also has a better scale up of number of function evaluations with the cluster size.
A survey on chromosomal structures and operators for exploiting topological linkages of genes
 In Genetic and Evolutionary Computation Conference
, 2003
"... Abstract. The building block hypothesis implies that the epistatic property of a given problem must be connected well to the linkage property of the employed representation and crossover operator in the design of genetic algorithms. A good handling of building blocks has much to do with topological ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
(Show Context)
Abstract. The building block hypothesis implies that the epistatic property of a given problem must be connected well to the linkage property of the employed representation and crossover operator in the design of genetic algorithms. A good handling of building blocks has much to do with topological linkages of genes in the chromosome. In this paper, we provide a taxonomy of the approaches that exploit topological linkages of genes. They are classified into three models: static linkage model, adaptive linkage model, and evolvable linkage model. We also provide an overview on the chromosomal structures, encodings, and operators supporting each of the models. 1
A Survey of Linkage Learning Techniques in Genetic and Evolutionary Algorithms
, 2007
"... This paper reviews and summarizes existing linkage learning techniques for genetic and evolutionary algorithms in the literature. It first introduces the definition of linkage in both biological systems and genetic algorithms. Then, it discusses the importance for genetic and evolutionary algorithms ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
(Show Context)
This paper reviews and summarizes existing linkage learning techniques for genetic and evolutionary algorithms in the literature. It first introduces the definition of linkage in both biological systems and genetic algorithms. Then, it discusses the importance for genetic and evolutionary algorithms to be capable of learning linkage, which is referred to as the relationship between decision variables. Existing linkage learning methods proposed in the literature are reviewed according to different facets of genetic and evolutionary algorithms, including the means to distinguish between good linkage and bad linkage, the methods to express or represent linkage, and the ways to store linkage information. Studies related to these linkage learning methods and techniques are also investigated in this survey.
Quality and efficiency of model building for genetic algorithms
 Proceedings of Genetic and Evolutionary Computation Conference 2004 (GECCO2004
, 2004
"... This paper investigates the linkage model building for genetic algorithms. By assuming a given quality of the linkage model, a analytical model of time to convergence is derived. Given the computational cost of building the linkage model, an estimated total computational time is obtained by using th ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
(Show Context)
This paper investigates the linkage model building for genetic algorithms. By assuming a given quality of the linkage model, a analytical model of time to convergence is derived. Given the computational cost of building the linkage model, an estimated total computational time is obtained by using the derived timetoconvergence model. The models are empirically verified. The results can be potentially used to decide whether applying a linkageidentification technique is worthwhile and give a guideline to speed up the linkage model building. 1
The Fundamental Problem with the Building Block Hypothesis
"... Skepticism of the building block hypothesis has previously been expressed on account of the weak theoretical foundations of this hypothesis and anomalies in the empirical record of the simple genetic algorithm. In this paper we focus on a more fundamental cause for skepticism—the extraordinary stren ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
(Show Context)
Skepticism of the building block hypothesis has previously been expressed on account of the weak theoretical foundations of this hypothesis and anomalies in the empirical record of the simple genetic algorithm. In this paper we focus on a more fundamental cause for skepticism—the extraordinary strength of some of the assumptions undergirding the building block hypothesis. As many of these assumptions have been embraced by the designers of so called “competent ” genetic algorithms, our critique is relevant to an appraisal of such algorithms. We argue that these assumptions are too strong to be acceptable without additional evidence. We then point out weaknesses in the arguments that have been provided in lieu of such evidence.
From DNA To Protein: Transformations And Their Possible Role In Linkage Learning
 Proceedings of the Seventh International Conference on Genetic Algorithms
"... This paper first presents an extended perspective of linkage using basic concepts developed in the SEARCH framework (Kargupta, 1995; Kargupta & Goldberg, 1996) and identifies detection of "appropriate" patterns or relations among the search space members as the fundamental and broader ..."
Abstract

Cited by 5 (4 self)
 Add to MetaCart
(Show Context)
This paper first presents an extended perspective of linkage using basic concepts developed in the SEARCH framework (Kargupta, 1995; Kargupta & Goldberg, 1996) and identifies detection of "appropriate" patterns or relations among the search space members as the fundamental and broader objective of linkage learning. It then explores the computational role of geneexpression (DNA!RNA!Protein transformations) in evolutionary search for relations, using an algebraic approach. It offers strong evidence to support the hypothesis that the transformations in geneexpression form fitness invariant symmetry groups over alphabet tuples that may be used to capture patterns or relations among the search space members. 1 Introduction Intracellular expression of genetic information in a living organism plays a critical role in the emergence of different forms of life. Different regions of DNA, the carrier of genetic information, are transcribed in different cells of an organism for producing messen...
Achieving a simple development model for 3D shapes: are chemicals necessary
 In: Proceedings of Genetic Evolutionary Computation Conference (GECCO
, 2007
"... Artificial Development Systems have been introduced as a technique aimed at increasing the scalability of evolutionary algorithms. Most commonly the development model is part of the evolutionary process, each individual developed during fitness evaluation. To achieve scalability it may be argued tha ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
Artificial Development Systems have been introduced as a technique aimed at increasing the scalability of evolutionary algorithms. Most commonly the development model is part of the evolutionary process, each individual developed during fitness evaluation. To achieve scalability it may be argued that the implicit requirements of evolvability and effectivity ( in terms of its resource requirements) are thus placed on the development model. To achieve an effective development model, one of the challenges is to find appropriate mechanisms from developmental biology and ways to implement them for the application in hand. This work presents a development model for the evolution and development of 3D shapes. The goal being to create a simple development model for any 3D shape. Further, this work provides a preliminary investigation into the usefulness of one of the mechanisms implemented in this model, that of chemicals.
ProblemIndependent Schema Synthesis for Genetic Algorithms
"... Abstract. As a preprocessing for genetic algorithms, static reordering helps genetic algorithms effectively create and preserve highquality schemata, and consequently improves the performance of genetic algorithms. In this paper, we propose a static reordering method independent of problemspecific ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
(Show Context)
Abstract. As a preprocessing for genetic algorithms, static reordering helps genetic algorithms effectively create and preserve highquality schemata, and consequently improves the performance of genetic algorithms. In this paper, we propose a static reordering method independent of problemspecific knowledge. One of the novel features of our reordering method is that it is applicable to any problem with no information about the problem. The proposed method constructs a weighted complete graph from the gene distances calculated from solutions with relatively high fitnesses, transforms them into a geneinteraction graph, and finds a gene rearrangement. Extensive experimental results showed significant improvement for a number of applications. 1
Simultaneity matrix for solving hierarchically decomposable functions
 Proceedings of the Genetic and Evolutionary Computation
, 2004
"... Abstract. The simultaneity matrix is an ℓ×ℓ matrix of numbers. It is constructed according to a set of ℓbit solutions. The matrix element mij is the degree of linkage between bit positions i and j. To exploit the matrix, we partition {0,...,ℓ − 1} by putting i and j in the same partition subset if ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
(Show Context)
Abstract. The simultaneity matrix is an ℓ×ℓ matrix of numbers. It is constructed according to a set of ℓbit solutions. The matrix element mij is the degree of linkage between bit positions i and j. To exploit the matrix, we partition {0,...,ℓ − 1} by putting i and j in the same partition subset if mij is significantly high. The partition represents the bit positions of building blocks (BBs). The partition is used in solution recombination so that the bits governed by the same partition subset are passed together. It can be shown that by exploiting the simultaneity matrix the hierarchically decomposable functions can be solved in a polynomial relationship between the number of function evaluations required to reach the optimum and the problem size. A comparison to the hierarchical Bayesian optimization algorithm (hBOA) is made. The hBOA uses less number of function evaluations than that of our algorithm. However, computing the matrix is 10 times faster and uses 10 times less memory than constructing Bayesian network. 1