- Authors:
- Franz Rothlauf,
- David E. Goldberg
From the Publisher:
In the field of genetic and evolutionary algorithms (GEAs), much theory and empirical study has been heaped upon operators and test problems, but problem representation has often been taken as given. This monograph breaks with this tradition and studies a number of critical elements of a theory of representations for GEAs and applies them to the empirical study of various important idealized test functions and problems of commercial import. The book considers basic concepts of representations, such as redundancy, scaling and locality and describes how GEAs'performance is influenced. Using the developed theory representations can be analyzed and designed in a theory-guided manner. The theoretical concepts are used as examples for efficiently solving integer optimization problems and network design problems. The results show that proper representations are crucial for GEAs'success.
Cited By
Rothlauf F Representations for Evolutionary Algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (1017-1037)- Rothlauf F Representations for Evolutionary Algorithms Proceedings of the Companion Conference on Genetic and Evolutionary Computation, (1048-1068)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (1046-1066)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (463-483)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, (526-546)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (726-746)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (518-538)
- Perfecto C, Bilbao M, Ser J and Ferro A (2017). A simulation-based quantitative analysis on the topological heritability of Dandelion-encoded meta-heuristics for tree optimization problems, Soft Computing - A Fusion of Foundations, Methodologies and Applications, 21:17, (4939-4952), Online publication date: 1-Sep-2017.
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Genetic and Evolutionary Computation Conference Companion, (489-509)
- Moraglio A and Sudholt D (2017). Principled design and runtime analysis of abstract convex evolutionary search, Evolutionary Computation, 25:2, (205-236), Online publication date: 1-Jun-2017.
- Rothlauf F Representations for Evolutionary Algorithms Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion, (413-434)
- Rothlauf F Representations for Evolutionary Algorithms Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, (345-366)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation, (323-344)
- hidalgo J, Colmenar J, Risco-Martín J, Sánchez-Lacruz C, Lanchares J, Garnica O and Díaz J Solving GA-hard problems with EMMRS and GPGPUs Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation, (1007-1014)
- Turner A and Miller J Cartesian Genetic Programming Revised Selected Papers of the 17th European Conference on Genetic Programming - Volume 8599, (222-233)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the 15th annual conference companion on Genetic and evolutionary computation, (335-356)
- Schulman R (2011). Beyond biology, ACM SIGEVOlution, 5:4, (14-24), Online publication date: 1-Nov-2011.
- Moraglio A Geometry of evolutionary algorithms Proceedings of the 13th annual conference companion on Genetic and evolutionary computation, (1439-1468)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the 13th annual conference companion on Genetic and evolutionary computation, (1191-1212)
- Krawiec K Semantically embedded genetic programming Proceedings of the 13th annual conference on Genetic and evolutionary computation, (1379-1386)
- Schulman R Beyond biology Proceedings of the 13th annual conference on Genetic and evolutionary computation, (7-14)
- Moraglio A Abstract convex evolutionary search Proceedings of the 11th workshop proceedings on Foundations of genetic algorithms, (151-162)
- Langdon W Elementary bit string mutation landscapes Proceedings of the 11th workshop proceedings on Foundations of genetic algorithms, (25-42)
- Doerr B, Johannsen D, Kötzing T, Neumann F and Theile M More effective crossover operators for the all-pairs shortest path problem Proceedings of the 11th international conference on Parallel problem solving from nature: Part I, (184-193)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the 12th annual conference companion on Genetic and evolutionary computation, (2535-2556)
- Moon J, Moon H and Cho Y A history-based scheduler for dynamic load balancing on distributed VOD server environments Proceedings of the 2010 international conference on Computational Science and Its Applications - Volume Part III, (269-276)
- Hugosson J, Hemberg E, Brabazon A and O'Neill M (2010). Genotype representations in grammatical evolution, Applied Soft Computing, 10:1, (36-43), Online publication date: 1-Jan-2010.
- Pelikan M and Katzgraber H Analysis of evolutionary algorithms on the one-dimensional spin glass with power-law interactions Proceedings of the 11th Annual conference on Genetic and evolutionary computation, (843-850)
- Wilson D and Kaur D (2009). Search, neutral evolution, and mapping in evolutionary computing, IEEE Transactions on Evolutionary Computation, 13:3, (566-590), Online publication date: 1-Jun-2009.
- Weise T, Niemczyk S, Skubch H, Reichle R and Geihs K A tunable model for multi-objective, epistatic, rugged, and neutral fitness landscapes Proceedings of the 10th annual conference on Genetic and evolutionary computation, (795-802)
- Rothlauf F Representations for evolutionary algorithms Proceedings of the 10th annual conference companion on Genetic and evolutionary computation, (2613-2638)
- Huang M, Huang H and Chen M (2007). Constructing a personalized e-learning system based on genetic algorithm and case-based reasoning approach, Expert Systems with Applications: An International Journal, 33:3, (551-564), Online publication date: 1-Oct-2007.
- Philemotte C and Bersini H A gestalt genetic algorithm Proceedings of the 9th annual conference on Genetic and evolutionary computation, (1328-1334)
- Paulden T and Smith D Some novel locality results for the blob code spanning tree representation Proceedings of the 9th annual conference on Genetic and evolutionary computation, (1320-1327)
- Soza C, Landa R, Riff M and Coello C A Cultural Algorithm with Operator Parameters Control for Solving Timetabling Problems Proceedings of the 12th international Fuzzy Systems Association world congress on Foundations of Fuzzy Logic and Soft Computing, (810-819)
- Liang Y, Leung K and Xu Z Neural Network Training Using Genetic Algorithm with a Novel Binary Encoding Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks, (371-380)
- Borenstein Y and Poli R Decomposition of fitness functions in random heuristic search Proceedings of the 9th international conference on Foundations of genetic algorithms, (123-137)
- Liang Y, Lueng K and Lee K A splicing/decomposable encoding and its novel operators for genetic algorithms Proceedings of the 8th annual conference on Genetic and evolutionary computation, (1225-1232)
- Branke J, Orbayı M and Uyar Ş The role of representations in dynamic knapsack problems Proceedings of the 2006 international conference on Applications of Evolutionary Computing, (764-775)
- Raidl G and Gottlieb J (2005). Empirical Analysis of Locality, Heritability and Heuristic Bias in Evolutionary Algorithms: A Case Study for the Multidimensional Knapsack Problem, Evolutionary Computation, 13:4, (441-475), Online publication date: 1-Dec-2005.
- Bekmann J and Hoffmann A Improved knowledge acquisition for high-performance heuristic search Proceedings of the 19th international joint conference on Artificial intelligence, (41-46)
- Borenstein Y and Poli R Information landscapes and problem hardness Proceedings of the 7th annual conference on Genetic and evolutionary computation, (1425-1431)
- Yossi B and Poli R Information landscapes and the analysis of search algorithms Proceedings of the 7th annual conference on Genetic and evolutionary computation, (1287-1294)
- Julstrom B The blob code is competitive with edge-sets in genetic algorithms for the minimum routing cost spanning tree problem Proceedings of the 7th annual conference on Genetic and evolutionary computation, (585-590)
- Cotta C On the application of evolutionary algorithms to the consensus tree problem Proceedings of the 5th European conference on Evolutionary Computation in Combinatorial Optimization, (58-67)
- O'Neill M and Brabazon A mGGA Proceedings of the 8th European conference on Genetic Programming, (311-320)
- Coello Coello C An introduction to evolutionary algorithms and their applications Proceedings of the 5th international conference on Advanced Distributed Systems, (425-442)
- Czarn A, MacNish C, Vijayan K and Turlach B Statistical exploratory analysis of genetic algorithms Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence, (1246-1252)
- Bekmann J and Hoffmann A HeurEAKA Proceedings of the 8th Pacific Rim International Conference on Trends in Artificial Intelligence, (361-372)
- Rothlauf F and Goldberg D (2003). Redundant representations in evolutionary computation, Evolutionary Computation, 11:4, (381-415), Online publication date: 1-Dec-2003.
- Rothlauf F Population sizing for the redundant trivial voting mapping Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII, (1307-1319)
Index Terms
- Representations for Genetic and Evolutionary Algorithms
Reviews
Pragyansmita Nayak
Genetic and evolutionary algorithms (GEA) have long been an active area of research, with the goal of solving problems that have been deemed impossible to solve by traditional methods. Though the basic mechanisms of genetic algorithms are simple, they can be used to solve a wide variety of problems. This is possible via a mixing and matching of problem representations, selection procedures, crossover operators, and mutation operators. This book addresses problem representation, and how it affects the performance of the algorithm. The entire text is arranged into nine chapters, which introduce genetic algorithms, the essential elements of a genetic algorithm, and analysis of binary representations and tree representations. A time-quality framework is presented that can be used for a theoretical analysis and design of the representation. This framework will definitely help readers to better understand the efficiency of a particular representation. This is one of the pioneer efforts in this direction. Previous work, like the building block hypothesis and schema theorem, was targeted at understanding why genetic algorithms work. Three essential elements of a genetic algorithm are the basis of the framework presented: redundancy, scaling, and distance distortion. Chapter 3 discusses how the three elements affect the performance of a genetic algorithm. As stated in the book, this framework is "not yet complete and there are still some gaps, rough approximations, unclear interdependencies, and also more, as yet unknown, elements." The developed framework focuses on uniformly scaled representations and exponentially scaled representations that are described, respectively, by scaling orders one and two. This choice is made due to the fact that there is no general theory on the influence of scaling on the performance of a GEA. The time-quality framework developed in chapter 4 is used in chapters 5 and 6 to study the effect of binary representation of integers and tree representations, respectively, on the performance of the genetic algorithm. The tree representations that are studied are Prufer numbers, link and node biased encoding, and characteristic vector encoding. The framework is not only used to study the effect of a representation on performance, but also to design and develop representations. Two representations for trees are presented in this book: network random keys (NetKeys) and direct tree representation (NetDir). Using the time-quality framework proposed in the book, the performance of genetic algorithms, and a comparison of the various representations available for trees, are presented as part of chapter 8. The problems involving tree structures that are considered in this chapter are the scalable test tree problem and the optimal communication spanning tree problem. The book concludes with a summary, conclusion, and pointers to future work. This book can't really have an end; it is just a beginning for a new paradigm, where genetic algorithms work, and we have a concrete theory to prove why they work. This enables solution developers to analytically compare the available options in the design of a genetic algorithm. Anyone interested in genetic algorithms will find this book handy. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Recommendations
Merits of using chromosome representations and shadow chromosomes in genetic algorithms for solving scheduling problems
Highlights- Chromosome representation in genetic algorithm (GA) is important but rarely examined.
AbstractTwo conjectures, the use of incomplete chromosome representations and shadow chromosomes may improve the performance of genetic algorithms (GAs), are examined in this study. The examination entails testing distributed flexible job shop ...
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...