- author = "Joerg Bremer and Sebastian Lehnhoff",
- title = "Towards Evolutionary Emergence",
- booktitle = "Position and Communication Papers of the 16th Conference on Computer Science and Intelligence Systems",
- year = "2021",
- editor = "Maria Ganzha and Leszek Maciaszek and Marcin Paprzycki and Dominik Slezak",
- pages = "55--60",
- address = "Online",
- month = "2-5 " # sep,
- organisation = "Polish Information Processing Society, Polskie Towarzystwo Informatyczne, Warszawa, Poland",
- publisher = "FedCSIS",
- keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, PSO",
- isbn13 = "78-83-962423-0-3",
- ISSN = "2300-5963",
-
URL = "
https://annals-csis.org/Volume_26/pliks/position.pdf",
-
URL = "https://annals-csis.org/proceedings/2021/drp/pdf/111.pdf",
-
DOI = "
doi:10.15439/2021F111",
- size = "6 pages",
- abstract = "With the upcoming era of large-scale, complex cyber-physical systems, also the demand for decentralized and self-organising algorithms for coordination rises. Often such algorithms rely on emergent behavior; local observations and decisions aggregate to some global behavior without any apparent, explicitly programmed rule. Systematically designing these algorithms targeted for a new orchestration or optimisation task is, at best, tedious and error prone. Suitable and widely applicable design patterns are scarce so far. We opt for a machine learning based approach that learns the necessary mechanisms for targeted emergent behavior automatically. To achieve this,we use Cartesian genetic programming. As an example that demonstrates the general applicability of this idea, we trained a swarm-based optimization heuristics and present first results showing that the learned swarm behavior is significantly better than just random search. We also discuss the encountered pitfalls and remaining challenges on the research agenda.",
- abstract = "Cyber-physical systems demand self-organizing algorithms that rely on emergent behaviour; local observations and decision aggregate to global behavior without explicitly programmed rules. Designing these algorithms is error prone. Widely applicable design patterns are scarce. We opt for a machine learning approach that learns mechanisms for targeted emergent behavior automatically. We use Cartesian genetic programming. As an example, that demonstrates the general applicability of this idea, we trained a swarm based heuristics and present first results showing that the learned swarm behavior is significantly better than just random search. We also discuss the encountered pitfalls and remaining challenges on the research agenda.",
-
notes = "Also {"}Annals of Computer Science and Information
Systems{"}, ACSIS, Volume 26, 55-60 (2021)
Sofia, Bulgaria
secretariat@fedcsis.org http://annals-csis.org/",
