Entropy-based Convergence Measurement in Discrete Estimation of Distribution Algorithms

Autor:	Jiri Ocenasek
Rok vydání:	2007
Předmět:	Binary entropy function Mathematical optimization Estimation of distribution algorithm Principle of maximum entropy Probabilistic logic Entropy (information theory) Bayesian network Maximum entropy spectral estimation Tournament selection Algorithm Mathematics
Zdroj:	Towards a New Evolutionary Computation ISBN: 9783540290063 Towards a New Evolutionary Computation
DOI:	10.1007/3-540-32494-1_2
Popis:	This chapter presents an entropy-based convergence measurement applicable to Estimation of Distribution Algorithms. Based on the measured entropy, the time point when the generation of new solutions becomes ineffective, can be detected. The proposed termination criterion is inherent to the complexity of used probabilistic models and automatically postpones the termination if inappropriate models are used.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::1092ebd57a39afc8885a7dc4bad5d245 https://doi.org/10.1007/3-540-32494-1_2 Zobrazit plný text záznamu