Document Detail


Population-based continuous optimization, probabilistic modelling and mean shift.
MedLine Citation:
PMID:  15901425     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Evolutionary algorithms perform optimization using a population of sample solution points. An interesting development has been to view population-based optimization as the process of evolving an explicit, probabilistic model of the search space. This paper investigates a formal basis for continuous, population-based optimization in terms of a stochastic gradient descent on the Kullback-Leibler divergence between the model probability density and the objective function, represented as an unknown density of assumed form. This leads to an update rule that is related and compared with previous theoretical work, a continuous version of the population-based incremental learning algorithm, and the generalized mean shift clustering framework. Experimental results are presented that demonstrate the dynamics of the new algorithm on a set of simple test problems.
Authors:
Marcus Gallagher; Marcus Frean
Related Documents :
18255395 - Recognizing multiple overlapping objects in image: an optimal formulation.
11108475 - A simple iterative approach to parameter optimization.
11694015 - Application of a mixed optimization strategy in the design of a pharmaceutical solid fo...
25196635 - Meta-analysis based variable selection for gene expression data.
11144585 - Interrelations among distortion-product phase-gradient delays: their connection to scal...
24619805 - Dynamics and forecast in a simple model of sustainable development for rural populations.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Evolutionary computation     Volume:  13     ISSN:  1063-6560     ISO Abbreviation:  Evol Comput     Publication Date:  2005  
Date Detail:
Created Date:  2005-05-19     Completed Date:  2005-08-08     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9513581     Medline TA:  Evol Comput     Country:  United States    
Other Details:
Languages:  eng     Pagination:  29-42     Citation Subset:  IM    
Affiliation:
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD 4072, Australia. marcusg@itee.uq.edu.au
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Cluster Analysis
Computational Biology / methods*
Evolution*
Evolution, Molecular
Models, Statistical
Models, Theoretical
Normal Distribution
Population Dynamics
Probability

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  The estimation of distributions and the minimum relative entropy principle.
Next Document:  Globally multimodal problem optimization via an estimation of distribution algorithm based on unsupe...