�ݺ�ߣshows by User: Posa

�ݺ�ߣshows by User: Posa / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: Posa / Mon, 09 Aug 2010 09:08:10 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: Posa GECCO 2010 OBUPM Workshop /slideshow/2010-geccoobupmsl-sincontdomains/4928608 2010-gecco-obupm-slsincontdomains-100809090811-phpapp01
Stochastic local search in continuous domain]]>
Stochastic local search in continuous domain]]> Mon, 09 Aug 2010 09:08:10 GMT /slideshow/2010-geccoobupmsl-sincontdomains/4928608 Posa@slideshare.net(Posa) GECCO 2010 OBUPM Workshop Posa Stochastic local search in continuous domain <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2010-gecco-obupm-slsincontdomains-100809090811-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> Stochastic local search in continuous domain

GECCO 2010 OBUPM Workshop from Petr Poۡ�Lk

]]> 317 2 https://cdn.slidesharecdn.com/ss_thumbnails/2010-gecco-obupm-slsincontdomains-100809090811-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 GECCO 2009 BBOB Workshop /Posa/gecco-2009-bbob-workshop posikgecco2009bbob-090716074944-phpapp01
]]>
]]> Thu, 16 Jul 2009 07:49:41 GMT /Posa/gecco-2009-bbob-workshop Posa@slideshare.net(Posa) GECCO 2009 BBOB Workshop Posa <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/posikgecco2009bbob-090716074944-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /><br>

GECCO 2009 BBOB Workshop from Petr Poۡ�Lk

]]> 308 2 https://cdn.slidesharecdn.com/ss_thumbnails/posikgecco2009bbob-090716074944-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 EvoNum 2008 /slideshow/evonum-2008/330392 evonum-2008-1207056416325470-4
The paper states two necessary conditions for an efficient and successful algorithm: (1) it must not converge on the slope of the fitness function, and (2) it must be allowed to converge in the valley. It also shows a simple Gaussian EDA with truncation selection which tries to fight the premature convergence by enlarging the ML estimate of standard deviation by a constant factor k. Finally, it is shown that a constant factor k that would satisfy the two stated requirements does not exist and that different factors for slope and for valley are needed.]]>
The paper states two necessary conditions for an efficient and successful algorithm: (1) it must not converge on the slope of the fitness function, and (2) it must be allowed to converge in the valley. It also shows a simple Gaussian EDA with truncation selection which tries to fight the premature convergence by enlarging the ML estimate of standard deviation by a constant factor k. Finally, it is shown that a constant factor k that would satisfy the two stated requirements does not exist and that different factors for slope and for valley are needed.]]> Tue, 01 Apr 2008 06:26:57 GMT /slideshow/evonum-2008/330392 Posa@slideshare.net(Posa) EvoNum 2008 Posa The paper states two necessary conditions for an efficient and successful algorithm: (1) it must not converge on the slope of the fitness function, and (2) it must be allowed to converge in the valley. It also shows a simple Gaussian EDA with truncation selection which tries to fight the premature convergence by enlarging the ML estimate of standard deviation by a constant factor k. Finally, it is shown that a constant factor k that would satisfy the two stated requirements does not exist and that different factors for slope and for valley are needed. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/evonum-2008-1207056416325470-4-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> The paper states two necessary conditions for an efficient and successful algorithm: (1) it must not converge on the slope of the fitness function, and (2) it must be allowed to converge in the valley. It also shows a simple Gaussian EDA with truncation selection which tries to fight the premature convergence by enlarging the ML estimate of standard deviation by a constant factor k. Finally, it is shown that a constant factor k that would satisfy the two stated requirements does not exist and that different factors for slope and for valley are needed.

EvoNum 2008 from Petr Poۡ�Lk

]]> 350 2 https://cdn.slidesharecdn.com/ss_thumbnails/evonum-2008-1207056416325470-4-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 GECCO 2007 /slideshow/gecco-2007/144025 gecco-2007-1193216766691524-2
]]>
]]> Wed, 24 Oct 2007 02:06:07 GMT /slideshow/gecco-2007/144025 Posa@slideshare.net(Posa) GECCO 2007 Posa <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gecco-2007-1193216766691524-2-thumbnail.jpg?width=120&height=120&fit=bounds" /><br>

GECCO 2007 from Petr Poۡ�Lk

]]> 430 3 https://cdn.slidesharecdn.com/ss_thumbnails/gecco-2007-1193216766691524-2-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-Posa-48x48.jpg?cb=1522781966 Hi, my name is Petr Po?��k and I am a researcher at the Czech Technical University in Prague, Dept. of Cybernetics. My research interests include evolutionary computation, machine learning, pattern recognition, and a bit of statistics. labe.felk.cvut.cz/~posik https://cdn.slidesharecdn.com/ss_thumbnails/2010-gecco-obupm-slsincontdomains-100809090811-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/2010-geccoobupmsl-sincontdomains/4928608 GECCO 2010 OBUPM Workshop https://cdn.slidesharecdn.com/ss_thumbnails/posikgecco2009bbob-090716074944-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds Posa/gecco-2009-bbob-workshop GECCO 2009 BBOB Workshop https://cdn.slidesharecdn.com/ss_thumbnails/evonum-2008-1207056416325470-4-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/evonum-2008/330392 EvoNum 2008