Abstract
The Machine Learning is one of the areas of Artificial Intelligence whose objective is the development of computational techniques for knowledge and building systems able to acquire knowledge automatically. One of the main challenges of learning algorithms is to maximize generalization. Thus the board machine, or a combination of more of a learning machine approach known in literature with the denomination ensemble along with the theory agents, become a promising alternative in this challenge. In this context, this research proposes the iEnsemble framework, which aims to provide a model of the ensemble through a multi-agent system architecture, where generalization, combination and learning are made through agents, through the performance of their respective roles. In the proposal, the agents follow each their life cycle and also perform the iStacking algorithm. This algorithm is based on Stacking method, which uses the reinforcement learning to define the result of the Ensemble. To validate the initial proposal of the framework, some experiments have been performed and the results obtained and limitations are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barbosa. B.H.G.: Computação Evolucionária e Máquinas de Comitê na Identificação de Sistemas Não-Lineares. Tese. Belo Horizonte: Universidade Federal de Minas Gerais. Programa de Pós-Graduação em Engenharia Elétrica (2009). 224:il
Bellifemine, F., Caire, G., Greewood, D.: Developing Multiagent Systems with JADE, p. 300. Wiley, New York (2007)
Bibimoune, M., Elghazel, H., Aussem, A.: An empirical comparison of supervised ensemble learning approaches. In: European Conference on Machine Learning, ECMLPKDD (2013)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Bordini, R.H., Hubner, J.F., Woolridge, M.: Programming Multiagent Systems in AgentSpeak using Jason, p. 292. Wiley, Sussex (2007)
Bradshaw, J.M.: An introduction to software agents. In: Software Agents, pp. 3–46. MIT Press, Massachusetts (1997). ISBN:0-262-52234-9
Breiman, L.: Bagging predictors. Mach. Learn. 24, 123–140 (1996)
Brenner, W., Zarnekow, R., Wittig, H.: Intelligent Software Agents: Foundations and Applications. Springer, Berlin (1998)
Calderón, J., López-Ortega, O., Castro-Espinoza, F.A.: A multi-agent ensemble of classifiers. In: Sidorov, G., Galicia-Haro, S.N. (eds.) MICAI 2015. LNCS, vol. 9413, pp. 499–508. Springer, Cham (2015). doi:10.1007/978-3-319-27060-9_41
Cervantes, L., Lee, J.-S., Lee, J.: Agent-based approach to distributed ensemble learning of fuzzy ARTMAP classifiers. In: Nguyen, N.T., Grzech, A., Howlett, Robert J., Jain, Lakhmi C. (eds.) KES-AMSTA 2007. LNCS, vol. 4496, pp. 805–814. Springer, Heidelberg (2007). doi:10.1007/978-3-540-72830-6_84
FIPA: Foundation for intelligent physical agents. Disponível em. http://www.fipa.org/. Acesso em: 06 mai. 2016
Guermeur, Y., Paugam-Moisy, H., Gallinari, P.: Multivariate linear regression on classifier outputs: a capacity study. In: Niklasson, L., Bodén, M., Ziemke, T. (eds.) ICANN 98 Perspectives in Neural Computing, pp. 693–698. Springer, London (1998). doi:10.1007/978-1-4471-1599-1_106
Guelpedi, M.V.C., Ribeiro, C.H., Omar, N.: Utilização de Aprendizagem por Reforço para Modelagem Autônoma do Aprendiz em um Tutor Inteligente. Simpósio Brasileiro de Informática na Educação. UFRJ (2003)
Hansen, L., Salomon, P.: Neural network ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 12, 993–1001 (1990)
Haykin, S.S.: Redes Neurais, 2nd edn. Bookman, New York (2001)
Haykin, S.S.: Neural Networks: A Comprehensive Foundation, 3rd edn. Prentice Hall, Upple Saddle River (2007)
Helmy, T. et al.: Adaptive ensemble and hybrid models for classification of bioinformatics datasets. Trans. Fuzzy Neural Netw. Bioinform. (2012)
JADE: Java agent development framework. Disponível em: http://jade.tilab.com. Acesso em: 5 mai. 2016
Kohavi, R.A.: Study of cross-validation and bootstrap for accuracy estimation and model selection. Int. Joint Conf. Artif. Intell. 14, 1137–1145 (1995)
Lima, C.A.M.: Comitê de Máquinas: Uma abordagem Unificada Empregando Máquinas de Vetores-Suporte. Tese. Campinas: Universidade Estadual de Campinas. Programa de Pós-Graduação em Engenharia Elétrica e de Computação (2004)
Magid, N., Giovanni, C., Bahri, P.: A methodology for the analysis and design of multiagent systems using JADE. Int. J. Comput. Syst. Sci. Eng. Spec. Issue Softw. Eng. for Multiagent Syst. (2006). Murdoch University, Austrália
Nilsson, N.J.: Learning Machines. McGraw-Hill, New York (1965)
Oza, N.C., Tumer, K.: Classifier ensembles: select real-world applications. Inf. Fusion 9, 4–20 (2008)
Perrone, M.P., Cooper, L.N.: When networks disagree: ensemble methods for hybrid neural networks. In: R. J
Rezende, S.O.: Sistemas Inteligentes: Fundamentos e aplicações, Barueri, São Paulo (2003)
Russel, S.J., Norvig, P.: Inteligência Artificial: A Modern Approach, p. 649. Prentice Hall, Upper Saddle River (2010)
Sacile, R., Paolucci, M.: Agent-based manufacturing and control systems, p. 288. CRC Press LLC, Flórida (2005)
Schapire, R.E.: The strength of weak learnability. Mach. Learn. 5(2), 197–227 (1990). Kluwer Academic Publishers, Boston
Seewald, A.K.: How to make stacking better and faster while also taking care of an unknown weakness. In: Proceedings of the Nineteenth International Conference on Machine Learning, pp. 554–561. Morgan Kaufmann Publishers (2002)
Silva, T.C.: Aprendizado de máquina em redes complexas: modelagem, análise e aplicações. Tese. São Carlos: Universidade de São Paulo –USP. Instituto de Ciências Matemáticas e de Computação (2012)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Junior, A.U., Silveira, R.A.: HIPS: Um Framework para Escalonamento Distribuído de Processos em Sistemas de Produção Utilizando Sistemas Multiagente. Avances en sistemas e informatica 7, 7–15 (2010)
Junior, A.U., de Freitas Filho, P.J., Silveira, R.A.: E-HIPS: an extention of the framework HIPS for stagger of distributed process in production systems based on multiagent systems and memetic algorithms. In: Sidorov, G., Galicia-Haro, S.N. (eds.) MICAI 2015. LNCS, vol. 9413, pp. 413–430. Springer, Cham (2015). doi:10.1007/978-3-319-27060-9_34
Villar, S.O.: Ensemble case-based learning for multi-agent systems. Doctoral Thesis, Universitat Autonoma de Barcelona (2005)
Vrba, P.: JAVA-based agent platform evaluation. In: Mařík, V., McFarlane, D., Valckenaers, P. (eds.) HoloMAS 2003. LNCS, vol. 2744, pp. 47–58. Springer, Heidelberg (2003). doi:10.1007/978-3-540-45185-3_5
Watking, C.J.C.H., Dayan, P.: Q-leaning. Mach. Learn. 8(3/4), 279–292 (1992)
Wolpert, D.: The lack of a priori distinctions between learning algorithms. Neural Comput. 8, 1341–1390 (1996)
Wozniack, M., Grana, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Inf. Fusion 16, 3–17 (2014). Elsevier
Yang, B., Braeuning, A., Johnson, K.R., Shi, Y.: General characteristics of temperature variation in China during the last two millennia. Geophys. Res. Lett. 29, 381–384 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Junior, A.U., de Freitas Filho, P.J., Azambuja Silveira, R., Costa e Lima, M.D., Reitz, R.W. (2017). iEnsemble: A Framework for Committee Machine Based on Multiagent Systems with Reinforcement Learning. In: Pichardo-Lagunas, O., Miranda-Jiménez, S. (eds) Advances in Soft Computing. MICAI 2016. Lecture Notes in Computer Science(), vol 10062. Springer, Cham. https://doi.org/10.1007/978-3-319-62428-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-62428-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-62427-3
Online ISBN: 978-3-319-62428-0
eBook Packages: Computer ScienceComputer Science (R0)