Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Alexander Hagg"'
Publikováno v:
Frontiers in Sports and Active Living, Vol 4 (2022)
This paper explores the role of artificial intelligence (AI) in elite sports. We approach the topic from two perspectives. Firstly, we provide a literature based overview of AI success stories in areas other than sports. We identified multiple approa
Externí odkaz:
https://doaj.org/article/1c7a889475504ccba6a749ab18599b0a
Autor:
Max Müller, Alexander Hagg, Robin Strickstrock, Marco Hülsmann, Alexander Asteroth, Karl N. Kirschner, Dirk Reith
Publikováno v:
Journal of Chemical Information and Modeling. 63:1872-1881
Autor:
Alexander Hagg
Publikováno v:
Natural Computing Series ISBN: 9783030795528
Here we describe quality diversity algorithms, a recent and powerful class of evolutionary algorithms that produces a diverse set of high-performing solutions. The optimization paradigm emphasizes phenotypic niching and egalitarian treatment of quali
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c606ed6cbcb1d785a4a1c4d9520e6f24
https://doi.org/10.1007/978-3-030-79553-5_12
https://doi.org/10.1007/978-3-030-79553-5_12
Autor:
Alexander Hagg, Alexander Asteroth, Christian Rasche, Kevin Bach, Mark Pfeiffer, Bundesinstitut für Sortwissenschaft
Künstliche Intelligenz hat in vielen Bereichen des gesellschaftlichen Lebens Einzug gehalten. Im vorliegenden Buch geben die Autoren einen Einblick in derzeitige nationale und internationale Einsatzgebiete und den Nutzen von KI, insbesondere des mas
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030637095
More and more, optimization methods are used to find diverse solution sets. We compare solution diversity in multi-objective optimization, multimodal optimization, and quality diversity in a simple domain. We show that multiobjective optimization doe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6c5a206014f905bf42291dc472f2e9a
https://doi.org/10.1007/978-3-030-63710-1_4
https://doi.org/10.1007/978-3-030-63710-1_4
Publikováno v:
GECCO '19: Genetic and Evolutionary Computation Conference, Prague, Czech Republic, July 13-17, 2019
GECCO (Companion)
GECCO (Companion)
Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be used in plac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1139b688cd18554d8878e6d8fe6ef5a
http://arxiv.org/abs/1907.07075
http://arxiv.org/abs/1907.07075
Publikováno v:
GECCO '19: Genetic and Evolutionary Computation Conference, Prague, Czech Republic, July 13-17, 2019
GECCO
GECCO
The initial phase in real world engineering optimization and design is a process of discovery in which not all requirements can be made in advance, or are hard to formalize. Quality diversity algorithms, which produce a variety of high performing sol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1b84ed705907127f587b77f9d888754
https://pub.h-brs.de/frontdoor/index/index/docId/4532
https://pub.h-brs.de/frontdoor/index/index/docId/4532
Publikováno v:
Soft Computing. 21:4859-4872
Maximal covering location problems have efficiently been solved using evolutionary computation. The multi-stage placement of charging stations for electric cars is an instance of this problem which is addressed in this study. It is particularly chall
Publikováno v:
Parallel Problem Solving from Nature – PPSN XV ISBN: 9783319992525
PPSN (1)
PPSN (1)
An iterative computer-aided ideation procedure is introduced, building on recent quality-diversity algorithms, which search for diverse as well as high-performing solutions. Dimensionality reduction is used to define a similarity space, in which solu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1145b9305aae90be81062ce5713824e7
https://doi.org/10.1007/978-3-319-99253-2_40
https://doi.org/10.1007/978-3-319-99253-2_40
Publikováno v:
GECCO
Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important when train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d11f6006a923a3cf186242cb81b559ad