Skip to main content

2015 | OriginalPaper | Buchkapitel

Agent-Based Neuro-Evolution Algorithm

verfasst von : Rafał Dreżewski, Krzysztof Cetnarowicz, Grzegorz Dziuban, Szymon Martynuska, Aleksander Byrski

Erschienen in: Agent and Multi-Agent Systems: Technologies and Applications

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Neural networks are nowadays widely used across many different areas, both enterprise and science related. Regardless of the field in which they are applied, optimization of their structure is usually needed. During the last decades many methods for this procedure have been proposed, among them techniques based on evolutionary algorithms. In this paper a new algorithm for optimization of neural networks architecture based on multi-agent evolutionary approach is proposed. Also results of preliminary experiments aimed at comparing the proposed technique to already existing ones are presented.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Byrski, A., Kisiel-Dorohinicki, M., Nawarecki, E.: Agent-based evolution of neural network architecture. In: Hamza, M. (ed.) Proceedings of the IASTED International Symposium: Applied Informatics. IASTED/ACTA Press (2002) Byrski, A., Kisiel-Dorohinicki, M., Nawarecki, E.: Agent-based evolution of neural network architecture. In: Hamza, M. (ed.) Proceedings of the IASTED International Symposium: Applied Informatics. IASTED/ACTA Press (2002)
2.
Zurück zum Zitat Cetnarowicz, K., Kisiel-Dorohinicki, M., Nawarecki, E.: The application of evolution process in multi-agent world (MAW) to the prediction system. In: Tokoro, M. (ed.) Proceedings of the 2nd International Conference on Multi-Agent Systems (ICMAS’96). AAAI Press (1996) Cetnarowicz, K., Kisiel-Dorohinicki, M., Nawarecki, E.: The application of evolution process in multi-agent world (MAW) to the prediction system. In: Tokoro, M. (ed.) Proceedings of the 2nd International Conference on Multi-Agent Systems (ICMAS’96). AAAI Press (1996)
3.
Zurück zum Zitat Dreżewski, R., Cetnarowicz, K.: Sexual selection mechanism for agent-based evolutionary computation. In: Shi, Y., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) Computational Science—ICCS 2007, 7th International Conference, Beijing, China, May 27–30, 2007, Proceedings, Part II. LNCS, vol. 4488, pp. 920–927. Springer, Berlin (2007) Dreżewski, R., Cetnarowicz, K.: Sexual selection mechanism for agent-based evolutionary computation. In: Shi, Y., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) Computational Science—ICCS 2007, 7th International Conference, Beijing, China, May 27–30, 2007, Proceedings, Part II. LNCS, vol. 4488, pp. 920–927. Springer, Berlin (2007)
4.
Zurück zum Zitat Dreżewski, R., Siwik, L.: Multi-objective optimization technique based on co-evolutionary interactions in multi-agent system. In: Giacobini, M., et al. (eds.) Applications of Evolutinary Computing, EvoWorkshops 2007: EvoCoMnet, EvoFIN, EvoIASP, EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog, Valencia, Spain, April 11–13, 2007, Proceedings. LNCS, vol. 4448, pp. 179–188. Springer, Berlin (2007) Dreżewski, R., Siwik, L.: Multi-objective optimization technique based on co-evolutionary interactions in multi-agent system. In: Giacobini, M., et al. (eds.) Applications of Evolutinary Computing, EvoWorkshops 2007: EvoCoMnet, EvoFIN, EvoIASP, EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog, Valencia, Spain, April 11–13, 2007, Proceedings. LNCS, vol. 4448, pp. 179–188. Springer, Berlin (2007)
5.
Zurück zum Zitat Dreżewski, R., Siwik, L.: Agent-based co-operative co-evolutionary algorithm for multi-objective optimization. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing—ICAISC 2008, 9th International Conference, Zakopane, Poland, June 22–26, 2008, Proceedings. LNCS, vol. 5097, pp. 388–397. Springer, Berlin (2008) Dreżewski, R., Siwik, L.: Agent-based co-operative co-evolutionary algorithm for multi-objective optimization. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing—ICAISC 2008, 9th International Conference, Zakopane, Poland, June 22–26, 2008, Proceedings. LNCS, vol. 5097, pp. 388–397. Springer, Berlin (2008)
6.
Zurück zum Zitat Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Parallel Problem Solving from Nature—PPSN IX, Procedings, pp. 671–680 (2006) Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Parallel Problem Solving from Nature—PPSN IX, Procedings, pp. 671–680 (2006)
7.
Zurück zum Zitat Floreano, D., Mattiussi, C.: Bio-inspired Artificial Intelligence. MIT Press (2008) Floreano, D., Mattiussi, C.: Bio-inspired Artificial Intelligence. MIT Press (2008)
8.
Zurück zum Zitat Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall (1999) Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall (1999)
9.
Zurück zum Zitat Kavzoglu, T., Vieira, C.A.O.: An analysis of artificial neural network pruning algorithms in relation to land cover classification accuracy. In: Proceedings of the Remote Sensing Society Student Conference, pp. 53–58. Oxford University Press (1998) Kavzoglu, T., Vieira, C.A.O.: An analysis of artificial neural network pruning algorithms in relation to land cover classification accuracy. In: Proceedings of the Remote Sensing Society Student Conference, pp. 53–58. Oxford University Press (1998)
11.
Zurück zum Zitat Mackey, M., Glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1977)CrossRef Mackey, M., Glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1977)CrossRef
12.
Zurück zum Zitat Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press (1998) Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press (1998)
13.
Zurück zum Zitat Mohraz, K., Protzel, P.: Flexnet a flexible neural network construction algorithm. In: Proceedings of the 4th European Symposium on Artifical Neural Networks (ESANN ’96), pp. 111–116 (1996) Mohraz, K., Protzel, P.: Flexnet a flexible neural network construction algorithm. In: Proceedings of the 4th European Symposium on Artifical Neural Networks (ESANN ’96), pp. 111–116 (1996)
14.
Zurück zum Zitat Moriarty, D.E., Miikkulainen, R.: Forming neural networks through efficient and adaptive coevolution. Evol. Comput. 5, 373–399 (1997)CrossRef Moriarty, D.E., Miikkulainen, R.: Forming neural networks through efficient and adaptive coevolution. Evol. Comput. 5, 373–399 (1997)CrossRef
15.
Zurück zum Zitat Precup, R.E., David, R.C., Petriu, E.M., Preitl, S., Paul, A.S.: Gravitational search algorithm-based tuning of fuzzy control systems with a reduced parametric sensitivity. In: Soft Computing in Industrial Applications, pp. 141–150. Springer (2011) Precup, R.E., David, R.C., Petriu, E.M., Preitl, S., Paul, A.S.: Gravitational search algorithm-based tuning of fuzzy control systems with a reduced parametric sensitivity. In: Soft Computing in Industrial Applications, pp. 141–150. Springer (2011)
16.
Zurück zum Zitat Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRef Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRef
17.
Zurück zum Zitat Ragg, T., Braun, H., Landsberg, H.: A comparative study of neural network optimization techniques. In: 13th International Conference On Machine Learning: Workshop Proceedings On Evolutionary Computing And Machine Learning, pp. 111–118. Springer (1997) Ragg, T., Braun, H., Landsberg, H.: A comparative study of neural network optimization techniques. In: 13th International Conference On Machine Learning: Workshop Proceedings On Evolutionary Computing And Machine Learning, pp. 111–118. Springer (1997)
18.
Zurück zum Zitat Wooldridge, M.: Introduction to Multiagent Systems. Wiley, New York (2001) Wooldridge, M.: Introduction to Multiagent Systems. Wiley, New York (2001)
19.
Zurück zum Zitat Yao, X., Liu, Y.: Evolving artificial neural networks through evolutionary programming. In: Fogel, L.J., et al. (ed.) Evolutionary Programming V: Proceedings of the 5th Annual Conference on Evolutionary Programming. MIT Press (1996) Yao, X., Liu, Y.: Evolving artificial neural networks through evolutionary programming. In: Fogel, L.J., et al. (ed.) Evolutionary Programming V: Proceedings of the 5th Annual Conference on Evolutionary Programming. MIT Press (1996)
20.
Zurück zum Zitat Zăvoianu, A.C., Bramerdorfer, G., Lughofer, E., Silber, S., Amrhein, W., Klement, E.P.: Hybridization of multi-objective evolutionary algorithms and artificial neural networks for optimizing the performance of electrical drives. Eng. Appl. Artif. Intell. 26(8), 1781–1794 (2013)CrossRef Zăvoianu, A.C., Bramerdorfer, G., Lughofer, E., Silber, S., Amrhein, W., Klement, E.P.: Hybridization of multi-objective evolutionary algorithms and artificial neural networks for optimizing the performance of electrical drives. Eng. Appl. Artif. Intell. 26(8), 1781–1794 (2013)CrossRef
Metadaten
Titel
Agent-Based Neuro-Evolution Algorithm
verfasst von
Rafał Dreżewski
Krzysztof Cetnarowicz
Grzegorz Dziuban
Szymon Martynuska
Aleksander Byrski
Copyright-Jahr
2015
DOI
https://doi.org/10.1007/978-3-319-19728-9_8