The Modular Genetic Algorithm: Exploiting Regularities in the Problem Space

Garibay, Özlem Özmen; Garibay, Iván; Wu, Annie S.

doi:10.1007/978-3-540-39737-3_73

Cited by 11 publications

(15 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Garibay et al introduced the Modular Genetic Algorithm, which was shown to signficantly outperform a standard Genetic Algorithm on a scalable problem with regularities [4]. The genome of an MGA individual is a vector of genes, where each gene is comprised of two components, the number-of-repetitions and some function which is repeated according to the value of the repetitions field.…”

Section: Modular Genetic Algorithmmentioning

confidence: 99%

“…Given the lack of suitable benchmark problems in the Genetic Algorithm literature that consider modularity, Garibay et al, [4] proposed the CheckerboardPattern discovery problem. In this problem a pattern of colours or states is imposed upon a two dimensional grid called the Checkerboard.…”

Section: The Checkerboard-pattern Discovery Problemmentioning

confidence: 99%

“…It is easily possible to scale the problem in terms of its complexity, modularity and regularity by increasing the size of the checkerboard, the number of patterns, and changing the number of components in each pattern, respectively. Example instances of this problem which are adopted in this study and in [4] are presented in Fig.1, which illustrates scaled-up versions of a 4X8 pattern to 8X16 and 16X32. Another problem instance tackled in this study of a 8X16 checkerboard pattern is also illustrated.…”

Section: The Checkerboard-pattern Discovery Problemmentioning

confidence: 99%

“…To this end a grammar-based Genetic Programming approach is adopted, in which the grammars represent the construction of syntactically correct genotypes of the Genetic Algorithm. In particular, we compare the representations and performance of the meta-Grammar Genetic Algorithm (mGGA) [3] to the Modular Genetic Algorithm (MGA) [4], highlighting some of the MGA's representational limitations, and demonstrate the potential of a more expressive representation in the form of the mGGA to scale to problems of increasing size and difficulty. Additionally, we consider the introduction of noise into the Checkerboard problem, in order to assess how the representations might generalise into noisy, real-world problem domains.…”

Section: Introductionmentioning

confidence: 99%

“…In this section we present two modular representations as implemented in the Modular GA [4] and the meta-Grammar GA [3].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Grammatical Genetic Programming Approach to Modularity in Genetic Algorithms

Hemberg

Gilligan

O’Neill

et al.

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The ability of Genetic Programming to scale to problems of increasing difficulty operates on the premise that it is possible to capture regularities that exist in a problem environment by decomposition of the problem into a hierarchy of modules. As computer scientists and more generally as humans we tend to adopt a similar divide-and-conquer strategy in our problem solving. In this paper we consider the adoption of such a strategy for Genetic Algorithms. By adopting a modular representation in a Genetic Algorithm we can make efficiency gains that enable superior scaling characteristics to problems of increasing size. We present a comparison of two modular Genetic Algorithms, one of which is a Grammatical Genetic Programming algorithm, the meta-Grammar Genetic Algorithm (mGGA), which generates binary string sentences instead of traditional GP trees. A number of problems instances are tackled which extend the Checkerboard problem by introducing different kinds of regularity and noise. The results demonstrate some limitations of the modular GA (MGA) representation and how the mGGA can overcome these. The mGGA shows improved scaling when compared the MGA.

show abstract

Section: Modular Genetic Algorithmmentioning

confidence: 99%

Section: The Checkerboard-pattern Discovery Problemmentioning

confidence: 99%

Section: The Checkerboard-pattern Discovery Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In this section we present two modular representations as implemented in the Modular GA [4] and the meta-Grammar GA [3].…”

Section: Introductionmentioning

confidence: 99%