000 03504nam a22005775i 4500
001 978-3-540-32373-0
003 DE-He213
005 20161121231021.0
007 cr nn 008mamaa
008 100806s2005 gw | s |||| 0|eng d
020 _a9783540323730
_9978-3-540-32373-0
024 7 _a10.1007/b10910
_2doi
050 4 _aQA75.5-76.95
072 7 _aUY
_2bicssc
072 7 _aUYA
_2bicssc
072 7 _aCOM014000
_2bisacsh
072 7 _aCOM031000
_2bisacsh
082 0 4 _a004.0151
_223
100 1 _aPelikan, Martin.
_eauthor.
245 1 0 _aHierarchical Bayesian Optimization Algorithm
_h[electronic resource] :
_bToward a new Generation of Evolutionary Algorithms /
_cby Martin Pelikan.
264 1 _aBerlin, Heidelberg :
_bSpringer Berlin Heidelberg,
_c2005.
300 _aXVIII, 166 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aStudies in Fuzziness and Soft Computing,
_x1434-9922 ;
_v170
505 0 _aFrom Genetic Variation to Probabilistic Modeling -- Probabilistic Model-Building Genetic Algorithms -- Bayesian Optimization Algorithm -- Scalability Analysis -- The Challenge of Hierarchical Difficulty -- Hierarchical Bayesian Optimization Algorithm -- Hierarchical BOA in the Real World.
520 _aThis book provides a framework for the design of competent optimization techniques by combining advanced evolutionary algorithms with state-of-the-art machine learning techniques. The book focuses on two algorithms that replace traditional variation operators of evolutionary algorithms by learning and sampling Bayesian networks: the Bayesian optimization algorithm (BOA) and the hierarchical BOA (hBOA). BOA and hBOA are theoretically and empirically shown to provide robust and scalable solution for broad classes of nearly decomposable and hierarchical problems. A theoretical model is developed that estimates the scalability and adequate parameter settings for BOA and hBOA. The performance of BOA and hBOA is analyzed on a number of artificial problems of bounded difficulty designed to test BOA and hBOA on the boundary of their design envelope. The algorithms are also extensively tested on two interesting classes of real-world problems: MAXSAT and Ising spin glasses with periodic boundary conditions in two and three dimensions. Experimental results validate the theoretical model and confirm that BOA and hBOA provide robust and scalable solution for nearly decomposable and hierarchical problems with only little problem-specific information.
650 0 _aComputer science.
650 0 _aComputer programming.
650 0 _aComputers.
650 0 _aArtificial intelligence.
650 0 _aApplied mathematics.
650 0 _aEngineering mathematics.
650 0 _aAlgorithms.
650 1 4 _aComputer Science.
650 2 4 _aTheory of Computation.
650 2 4 _aAppl.Mathematics/Computational Methods of Engineering.
650 2 4 _aArtificial Intelligence (incl. Robotics).
650 2 4 _aProgramming Techniques.
650 2 4 _aAlgorithms.
650 2 4 _aApplications of Mathematics.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783540237747
830 0 _aStudies in Fuzziness and Soft Computing,
_x1434-9922 ;
_v170
856 4 0 _uhttp://dx.doi.org/10.1007/b10910
912 _aZDB-2-ENG
950 _aEngineering (Springer-11647)
999 _c507357
_d507357