A Conditional Dependency Based Probabilistic Model Building Grammatical Evolution

Hyun-Tae KIM
Hyun-Kyu KANG
Chang Wook AHN

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D    No.7    pp.1937-1940
Publication Date: 2016/07/01
Publicized: 2016/04/11
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8004
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
Keyword: 
grammatical evolution,  probabilistic modeling,  context-free grammars,  automatic program generation,  

Full Text: PDF(349KB)>>
Buy this Article


Summary: 
In this paper, a new approach to grammatical evolution is presented. The aim is to generate complete programs using probabilistic modeling and sampling of (probability) distribution of given grammars. To be exact, probabilistic context free grammars are employed and a modified mapping process is developed to create new individuals from the distribution of grammars. To consider problem structures in the individual generation, conditional dependencies between production rules are incorporated into the mapping process. Experiments confirm that the proposed algorithm is more effective than existing methods.

open access publishing via