Filters








171,964 Hits in 7.9 sec

On averaging the best samples in evolutionary computation [article]

Laurent Meunier, Yann Chevaleyre, Jeremy Rapin, Clément W. Royer, Olivier Teytaud
2020 arXiv   pre-print
Choosing the right selection rate is a long standing issue in evolutionary computation.  ...  In the continuous unconstrained case, we prove mathematically that a single parent μ=1 leads to a sub-optimal simple regret in the case of the sphere function.  ...  Introduction In evolutionary computation, the selected population size often depends linearly on the total population size, with a ratio between 1/4 and 1/2: 0.270 is proposed in [4] , [10, 5] suggest  ... 
arXiv:2004.11685v3 fatcat:o74quqeay5g5dnrz2mxwvm5ypa

On Averaging the Best Samples in Evolutionary Computation [chapter]

Laurent Meunier, Yann Chevaleyre, Jeremy Rapin, Clément W. Royer, Olivier Teytaud
2020 Lecture Notes in Computer Science  
Choosing the right selection rate is a long standing issue in evolutionary computation.  ...  In the continuous unconstrained case, we prove mathematically that a single parent μ = 1 leads to a suboptimal simple regret in the case of the sphere function.  ...  Introduction In evolutionary computation, the selected population size often depends linearly on the total population size, with a ratio between 1/4 and 1/2: 0.270 is proposed in [4, 5, 10] suggest 1  ... 
doi:10.1007/978-3-030-58115-2_46 fatcat:dozgialgizerjkxpuwbrf3zeua

A framework for evolutionary optimization with approximate fitness functions

Yaochu Jin, M. Olhofer, B. Sendhoff
2002 IEEE Transactions on Evolutionary Computation  
It is not unusual that an approximate model is needed for fitness evaluation in evolutionary computation.  ...  In this case, the convergence properties of the evolutionary algorithm are unclear due to the approximation error of the model.  ...  ACKNOWLEDGMENT The authors thank D. B. Fogel and anonymous reviewers for their valuable comments and helpful suggestions, which improved the presentation of the paper greatly.  ... 
doi:10.1109/tevc.2002.800884 fatcat:xflhjah7x5az5exbhprc65avla

Evolutionary-Neural Hybrid Agents for Architecture Search [article]

Krzysztof Maziarz, Mingxing Tan, Andrey Khorlin, Marin Georgiev, Andrea Gesmundo
2020 arXiv   pre-print
In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS).  ...  On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application.  ...  ACKNOWLEDGMENTS We thank Zalan Borsos, Stanisław Jastrzębski, Quentin de Laroussilhe, Kuang-Yu Samuel Chang and all the members of Google AI that have influenced this work.  ... 
arXiv:1811.09828v4 fatcat:7czgn6czfjgw5cgczus4y2j5u4

Using multiple offspring sampling to guide genetic algorithms to solve permutation problems

Antonio LaTorre, José M. Peña, Victor Robles, Santiago Muelas
2008 Proceedings of the 10th annual conference on Genetic and evolutionary computation - GECCO '08  
In this contribution, we propose a new theoretical formalism, called Multiple Offspring Sampling (MOS).  ...  The results on several instances of this problem show that most of the combined techniques outperform the results obtained by single ones.  ...  The average of these corrected wins is also weighted by the number of techniques in the combination. In the previous example, the number of wins has weight 1/3 to compute the average.  ... 
doi:10.1145/1389095.1389307 dblp:conf/gecco/LaTorrePRM08 fatcat:qmdk66jffzactpo7en3hskexca

Pyramid Matting: A Resource-Adaptive Multi-Scale Pixel Pair Optimization Framework for Image Matting

Liang Yihui, Feng Fujian, Cai Zhaoquan
2020 IEEE Access  
Pixel-pair-optimization-based image matting approaches have been shown very successful in estimating the opacity of the foreground by searching for the best pair of foreground and background pixels for  ...  However, extant approaches encounter difficulties in adapting to the changes of available computing resources, which limits the application of image matting.  ...  MOEAMCD-PMF provided alpha mattes with lower average MSE than MOEAMCD on 15 out of 27 images in case one.  ... 
doi:10.1109/access.2020.2995207 fatcat:amn73bfsc5fkxcklbdorelet4i

Active control for traffic lights in regions and corridors: an approach based on evolutionary computation

Samara Soares Leal, Paulo Eduardo Maciel de Almeida, Edward Chung
2017 Transportation Research Procedia  
The main consequence of this phenomenon refers to the increase of urban congestions, of average delays caused by vehicles waiting on traffic lights and of number of stops.  ...  The main consequence of this phenomenon refers to the increase of urban congestions, of average delays caused by vehicles waiting on traffic lights and of number of stops.  ...  Paulo Almeida is deeply grateful to Edward Chung and STRC personnel at QUT, Brisbane, Australia, for the kind reception in the research group during his sabbatical, between 2013 and 2014.  ... 
doi:10.1016/j.trpro.2017.05.140 fatcat:enwklshpwbeu7mhchuvn4rxzia

Optimizing low-discrepancy sequences with an evolutionary algorithm

François-Michel De Rainville, Christian Gagné, Olivier Teytaud, Denis Laurendeau
2009 Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09  
This paper proposes the use of evolutionary algorithms to evolve these permutations, in order to optimize a discrepancy measure.  ...  Many fields rely on some stochastic sampling of a given complex space.  ...  Acknowledgments The authors acknowledge the financial support of Defence Research and Development Canada.  ... 
doi:10.1145/1569901.1570101 dblp:conf/gecco/RainvilleGTL09 fatcat:mtynftw2drhybnc62nkrfctbl4

Shaping fitness function for evolutionary learning of game strategies

Marcin Szubert, Wojciech Jaśkowski, Paweł Liskowski, Krzysztof Krawiec
2013 Proceeding of the fifteenth annual conference on Genetic and evolutionary computation conference - GECCO '13  
In evolutionary learning of game-playing strategies, fitness evaluation is based on playing games with certain opponents.  ...  In an extensive computational experiment we employ these methods to learn Othello strategies and assess both the absolute and relative performance of the elaborated players.  ...  For this reason, solving test-based problems with evolutionary computation requires substituting the original performance measure with a computationally cheaper counterpart that drives the search process  ... 
doi:10.1145/2463372.2463513 dblp:conf/gecco/SzubertJLK13 fatcat:zta53kkyrrcbfk3zim2gkjkgpa

Quantum-Enhanced Selection Operators for Evolutionary Algorithms [article]

David Von Dollen, Sheir Yarkoni, Daniel Weimer, Florian Neukart, Thomas Bäck
2022 arXiv   pre-print
We observe a performance gain in average number of generations to convergence for the quantum-enhanced elitist selection operator in comparison to classical on the OneMax function.  ...  to sample low energy solutions for the selection mechanism.  ...  𝐺𝐷 Genotype diversity, the average amount of diversity measured between genotypes in a population.  ... 
arXiv:2206.10743v1 fatcat:2fmczcizszctrjs366no3unv4a

Evolutionary Learning of Technical Trading Rules without Data-Mining Bias [chapter]

Alexandros Agapitos, Michael O'Neill, Anthony Brabazon
2010 Parallel Problem Solving from Nature, PPSN XI  
For the first time in the evolutionary computation literature, a comprehensive test for a rule's statistical significance using Hansen's Superior Predictive Ability is explicitly taken into account in  ...  Empirical results on a spot foreign-exchange market index suggest that increased out-of-sample performance can be obtained after accounting for data-mining bias effects in a multi-objective fitness function  ...  Acknowledgement This publication has emanated from research conducted with the financial support of Science Foundation Ireland under Grant Number 08/SRC/FM1389.  ... 
doi:10.1007/978-3-642-15844-5_30 dblp:conf/ppsn/AgapitosOB10 fatcat:fylq4qwzgnad5ek3pnd3tcc6oa

A comprehensive survey of fitness approximation in evolutionary computation

Y. Jin
2003 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
In this paper, a comprehensive survey of the research on fitness approximation in evolutionary computation is presented.  ...  Evolutionary algorithms (EAs) have received increasing interests both in the academy and industry.  ...  For example, some strategies use the best individuals to replace the worse ones in the train-ing samples, or the ones that are randomly selected.  ... 
doi:10.1007/s00500-003-0328-5 fatcat:2bgqqkyslnbd3btq5qpbuc4kiy

Document Clustering with Evolutionary Systems through Straight-Line Programs "slp"

José Luis Castillo Sequera, José Raúl Fernández del Castillo Diez, León Gonzalez Sotos
2012 Journal of Intelligent Learning Systems and Applications  
In this paper, we show a clustering method supported on evolutionary algorithms with the paradigm of linear genetic programming.  ...  It has been used as a theoretical model in Computer Algebra, and our purpose is to reuse it in a completely different context.  ...  Acknowledgements We would like to thank Departament of Computer Science of University of Alcalá for its support and for providing this research oportunity. Work  ... 
doi:10.4236/jilsa.2012.44032 fatcat:zivdqdzle5fdzatjiwsoi2jqfq

Measuring Generalization Performance in Coevolutionary Learning

Siang Yew Chong, P. Tino, Xin Yao
2008 IEEE Transactions on Evolutionary Computation  
Given that the true value may not be determined by solving analytically a closed-form formula and is computationally prohibitive, we propose an estimation procedure that computes the average performance  ...  For game-playing, it is well-known that one is more interested in the generalization performance against a biased and diverse sample of "good" test strategies.  ...  The authors are grateful to The Centre of Excellence for Research in Computational Intelligence and Applications (CERCIA), School of Computer Science, The University of Birmingham, UK, for providing computing  ... 
doi:10.1109/tevc.2007.907593 fatcat:gydso35uifda7n5r2fcxrmil54

Recombination smooths the time-signal disrupted by latency in within-host HIV phylogenies [article]

Lauren A Castro, Thomas Leitner, Ethan Romero-Severson
2022 bioRxiv   pre-print
In effect, recombination averages over extant heterogeneity, whether it stems from mixed time-signals or population bottlenecks.  ...  Further, we establish that the signals of latency and recombination can be observed in phylogenetic trees despite being an incorrect representation of the true evolutionary history.  ...  in the simulated sequence (Fig 1 ), 2 ) compute an average distance matrix from the population of binary trees, and 3) compute a single phylogeny from the average distance matrix.  ... 
doi:10.1101/2022.02.22.481498 fatcat:rsl2yst7nvbyxkwydv65gpn4dm
« Previous Showing results 1 — 15 out of 171,964 results