Growth of self-canceling code in evolutionary systems

Zhang, Xue; Soule, Terence

doi:10.1145/1143997.1144034

“…It has often been thought that these redundancies may protect programs from the destructive effects of GP crossover [18], [27], [26] by reducing the chances of crossover/mutation points being selected within highly fit portions of a program, and that genetic systems are under evolutionary pressure to create these redundancies in order to increase the "robustness" of fit solutions [31]. Additionally, redundancies may contain valuable genetic materials that can be recombined in future generations to form better solutions [18].…”

Section: Introductionmentioning

confidence: 99%

Effects of program simplification on simple building blocks in Genetic Programming

Wong

¹

,

Zhang

²

2007

2007 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

This paper investigates the effects on building blocks of using simplification in a Genetic Programming (GP) system to combat the problem of code bloat. The evolved genetic programs are simplified online during the evolutionary process using algebraic simplification rules and hashing techniques. A simplified form of building block (numerical-nodes) is tracked throughout individual GP runs both when using or not using online simplification of evolved genetic programs. The results suggest that online simplification disrupts existing potential building blocks during the evolution process. However, GP with simplification is capable of creating new building blocks which are used to form a more accurate solution, when compared to the standard GP. The effectiveness of GP systems utilising simplification can be correlated to the creation of these new building blocks.

show abstract

“…Zhang and Soule [103] also work on the basis of introns and 'genes' which either do not influence fitness or have very little effect. Genetically robust solutions are solutions that are less likely to be degraded by genetic operators, such as crossover.…”

Section: The Problem and Causesmentioning

confidence: 99%

“…It has often been thought that the redundancies that make up a large part of code bloat may protect programs from the destructive effects of GP crossover [59,90,89] by reducing the chances of crossover/mutation points being selected within highly fit portions of a program, and that genetic systems are under evolutionary pressure to create these redundancies in order to increase the "robustness" of fit solutions [103]. Additionally, redundancies may contain valuable genetic materials that can be recombined in future generations to form better solutions [59].…”

Section: Introductionmentioning

confidence: 99%

Removing Redundancy and Reducing Fitness Evaluation Costs in Genetic Programming

Wong¹

0

View full text Add to dashboard Cite

<p>One of the greater issues in Genetic Programming (GP) is the computational effort required to run the evolution and discover a good solution. Phenomena such as program bloating (where genetic programs rapidly grow in size) can quickly exhaust available memory resources and slow down the evolutionary process, while the heavy cost of performing fitness evaluation can make problems which have a lot of available data very slow to solve. These issues may limit GP in some tasks it can appropriately be applied to, as well as inhibit its applications in time/space sensitive environments. In this thesis, we look at developing solutions to some of these issues in GP computational cost. First, we develop an algebraic program simplification method based on simple rules and hashing techniques, and use this method in conjunction with the standard GP on a variety of tasks. Our results suggest that program simplification can lead to a significant reduction in program size, while not significantly changing the effectiveness of the systems in finding solution programs. Secondly, we analyse the effects of program simplification on the internal GP "building blocks" to investigate whether simplification is a destructive or constructive force. Using two models for building blocks (numerical-nodes and the more complex fixed-depth subtree), we track building blocks through GP runs on a symbolic regression problem, both with and without using simplification. We find that the program simplification process can both disrupt and construct building blocks in the GP populations. However, GP systems using simplification appear to retain important building blocks, and the simplification process appears to lead to an increase in genetic diversity. These may help explain why using simplification does not reduce the effectiveness of GP systems in solving tasks. Lastly, we develop two methods of reducing the cost of fitness evaluation by reducing the number of node evaluations performed. The first method is elitism avoidance, which avoids re-evaluating programs which have been placed in the population using elitismreproduction. Thismethod reduces the CPU time for evolving solutions for six different GP tasks. The second method is a subtree caching mechanism which store fitness evaluations for subtrees in a cache so that they may be fetched when these subtrees are encountered in future fitness evaluations. Results suggest that using this mechanism can significantly reduce both the number of node evaluations and the overall CPU time used in evolving solutions, without reducing the fitness of the solutions produced.</p>

show abstract

“…Zhang and Soule [103] also work on the basis of introns and 'genes' which either do not influence fitness or have very little effect. Genetically robust solutions are solutions that are less likely to be degraded by genetic operators, such as crossover.…”

Section: The Problem and Causesmentioning

confidence: 99%

“…It has often been thought that the redundancies that make up a large part of code bloat may protect programs from the destructive effects of GP crossover [59,90,89] by reducing the chances of crossover/mutation points being selected within highly fit portions of a program, and that genetic systems are under evolutionary pressure to create these redundancies in order to increase the "robustness" of fit solutions [103]. Additionally, redundancies may contain valuable genetic materials that can be recombined in future generations to form better solutions [59].…”

Section: Introductionmentioning

confidence: 99%

Removing Redundancy and Reducing Fitness Evaluation Costs in Genetic Programming

Wong¹

0

View full text Add to dashboard Cite

<p>One of the greater issues in Genetic Programming (GP) is the computational effort required to run the evolution and discover a good solution. Phenomena such as program bloating (where genetic programs rapidly grow in size) can quickly exhaust available memory resources and slow down the evolutionary process, while the heavy cost of performing fitness evaluation can make problems which have a lot of available data very slow to solve. These issues may limit GP in some tasks it can appropriately be applied to, as well as inhibit its applications in time/space sensitive environments. In this thesis, we look at developing solutions to some of these issues in GP computational cost. First, we develop an algebraic program simplification method based on simple rules and hashing techniques, and use this method in conjunction with the standard GP on a variety of tasks. Our results suggest that program simplification can lead to a significant reduction in program size, while not significantly changing the effectiveness of the systems in finding solution programs. Secondly, we analyse the effects of program simplification on the internal GP "building blocks" to investigate whether simplification is a destructive or constructive force. Using two models for building blocks (numerical-nodes and the more complex fixed-depth subtree), we track building blocks through GP runs on a symbolic regression problem, both with and without using simplification. We find that the program simplification process can both disrupt and construct building blocks in the GP populations. However, GP systems using simplification appear to retain important building blocks, and the simplification process appears to lead to an increase in genetic diversity. These may help explain why using simplification does not reduce the effectiveness of GP systems in solving tasks. Lastly, we develop two methods of reducing the cost of fitness evaluation by reducing the number of node evaluations performed. The first method is elitism avoidance, which avoids re-evaluating programs which have been placed in the population using elitismreproduction. Thismethod reduces the CPU time for evolving solutions for six different GP tasks. The second method is a subtree caching mechanism which store fitness evaluations for subtrees in a cache so that they may be fetched when these subtrees are encountered in future fitness evaluations. Results suggest that using this mechanism can significantly reduce both the number of node evaluations and the overall CPU time used in evolving solutions, without reducing the fitness of the solutions produced.</p>

show abstract

Growth of self-canceling code in evolutionary systems

Cited by 4 publications

References 14 publications

Effects of program simplification on simple building blocks in Genetic Programming

Effects of program simplification on simple building blocks in Genetic Programming

Removing Redundancy and Reducing Fitness Evaluation Costs in Genetic Programming

Removing Redundancy and Reducing Fitness Evaluation Costs in Genetic Programming

Contact Info

Product

Resources

About