Grammatical Swarm: The generation of programs by social programming

Authors:
Michael O'Neill;Anthony Brabazon
Affiliations:
Natural Computing Research & Applications Group, University College Dublin, Dublin, Ireland;Natural Computing Research & Applications Group, University College Dublin, Dublin, Ireland
Venue:
Natural Computing: an international journal
Year:
2006

Citing 0
Cited 10

Enhanced generalized ant programming (EGAP)

Proceedings of the 10th annual conference on Genetic and evolutionary computation
GEVA: grammatical evolution in Java

ACM SIGEVOlution
Shape grammars and grammatical evolution for evolutionary design

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Genotype representations in grammatical evolution

Applied Soft Computing
Grammar-based Genetic Programming: a survey

Genetic Programming and Evolvable Machines
Polynomial modeling for time-varying systems based on a particle swarm optimization algorithm

Information Sciences: an International Journal
Identifying desirable game character behaviours through the application of evolutionary algorithms to model-driven engineering metamodels

SSBSE'11 Proceedings of the Third international conference on Search based software engineering
Parse-matrix evolution for symbolic regression

Engineering Applications of Artificial Intelligence
Speech enhancement strategy for speech recognition microcontroller under noisy environments

Neurocomputing
A hybrid noise suppression filter for accuracy enhancement of commercial speech recognizers in varying noisy conditions

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study examines Social Programming, that is, the construction of programs using a Social Swarm algorithm based on Particle Swarm Optimization. Each individual particle represents choices of program construction rules, where these rules are specified using a Backus---Naur Form grammar. This study represents the first instance of a Particle Swarm Algorithm being used to generate programs. A selection of benchmark problems from the field of Genetic Programming are tackled and performance is compared to Grammatical Evolution. The results demonstrate that it is possible to successfully generate programs using the Grammatical Swarm technique. An analysis of the Grammatical Swarm approach is presented on the dynamics of the search. It is found that restricting the search to the generation of complete programs, or with the use of a ratchet constraint forcing individuals to move only if a fitness improvement has been found, can have detrimental consequences for the swarms performance and dynamics.