particle swarm applied to a neural network as backpropagation for optimizing game time

Authors

  • Ana Paula Capeletti Ramos Almeida Universidade Tecnológica Federal do Paraná
  • Evandro Alves Nakajima Federal Technological University of Paraná

Keywords:

Machine learning., Particle swarm optimization., Chrome game.

Abstract

This work explores the particle swarm algorithm as a backpropagation of a neural network, based on the Google Chrome offline game, which is an endless runner (game where the character runs automatically and continuously to the right), with the objective of maximizing time of play. To optimize the network, Particle Swarm Opmization (PSO) was used, which is a backpropagation technique created to simulate the behavior of a flock of birds. It can be concluded that the PSO algorithm was efficient for the optimization process since the players managed to reach the maximum time stipulated in just 4 rounds.

Downloads

Download data is not yet available.

Author Biographies

Ana Paula Capeletti Ramos Almeida, Universidade Tecnológica Federal do Paraná

Graduanda. Universidade Tecnológica Federal do Paraná. Orcid: 0000-0002-1992-4575

Evandro Alves Nakajima, Federal Technological University of Paraná

He has a degree in Mathematics from the State University of Maringá (2010) and a master's degree in Mathematics from the University of São Paulo (2013). PhD student in Chemical Engineering at the State University of Western Paraná. He is currently an assistant professor at the Federal Technological University of Paraná. He has experience in the areas of Mathematics and Chemical Engineering.

References

AGUIAR, F. G. Utilização de Redes Neurais Artificiais para detecção de padrões de vazamento em dutos. 2010. p.95. Tese de Doutorado, Térmica e Fluidos - Universidade de São Paulo, São Paulo, 2010.

BÖRSTLER, J.; BRUCE, K.; MICHIELS, I. Sixth workshop on pedagogies and tools for learning object oriented concepts. ECOOP, p. 84-87, 2003. Acesso em: 04 out. 2020.

HARBOUR, J. S. Programação de Games com Java. Tradução da 2.ed. Boston: Cengage Learning, 2010.

HAYKIN, S. Redes Neurais: princípios e prática. Porto Alegre: Bookman Editora, 2007.

KENNEDY, J.; EBERHART, R. Particle swarm optimization. IEEE, p. 1942-1948, 1995. Acesso em: 04 out. 2020.

KHARE, A.; RANGNEKAR, S. A review of particle swarm optimization and its applications in solar photovoltaic system. Applied Soft Computing, v. 13, n. 5, p. 2997-3006, 2013. Acesso em: 04 jan. 2021.

MARINI, F.; WALCZAK, B. Particle swarm optimization (PSO). A tutorial. Chemometrics and Intelligent Laboratory Systems, v. 149, p. 153-165, 2015. Acesso em: 07 out. 2020.

MARTINIANO, A.; FERREIRA, R.P.; FERREIRA, A.; FERREIRA, A.; SASSI, R.J. Utilizando uma rede neural artificial para aproximação da função de evolução do sistema de Lorentz. Revista Produção e Desenvolvimento, v. 2, n. 1, p. 26-38, abr. 2016. Acesso em: 01 out. 2020.

MANZANO, J. A. N. G.; JÚNIOR, R. A. C. Programação de computadores com java. Saraiva Educação SA, 2014.

MCCULLOCH, W. S.; PITTS, W. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, v. 5, n. 4, p. 115-133, 1943. Acesso em: 02 jan. 2021.

MOHAMMAD, A. A.; SOHRAB, Z.; ALI, L.; ALI, E.; IOANNIS, C. Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization. Geophysical Prospecting, v. 61, n. 3, p. 582-598, 2013. Acesso em: 18 jan. 2021.

NORVIG, P.; RUSSELL, S. Inteligência Artificial: Tradução da 3.ed. Rio de Janeiro: Elsevier Brasil, 2013.

ORACLE. Class Canvas. Java Platform. 7.ed, 2018. Disponível em: <https://docs.oracle.com/javase/7/docs/api/java/awt/Canvas.html>. Acesso em: 06 out. 2020.

POLAK, E., Computational Methods in Optimization: A Unified Approach. Cambridge: Academic Press, 1971.

RUMELHART D. E.; HINTON G. E.; WILLIANS R. J. Learinig representations by back propagation error. Nature, v. 323, nº. 9, p. 533-536, 1986. Acesso em: 22 jan. 2021.

SARAMAGO, S. F. P.; Métodos de otimização randômica: Algoritmos genéricos e Simulated annealling. Sociedade Brasileira de Matemática Aplicada e Computacional, v. 6, p. 25-26, 2003. Acesso em: 01 abr. 2021.

SLOWIK, A.; BIALKO, M. Training of Artificial Neural Networks Using Differential Evolution Algorithm, IEEE, p. 60-65. 2008. Acesso em: 02 out. 2020.

TAVARES, L.V.; Correia, F. N. Optimização linear e não linear: conceitos, métodos e algortimos. 2.ed. Lisboa: Livraria Portugal, 1986.

VAHLDICK, A. Uma experiência lúdica no ensino de programação orientada a objetos. XVIII Simpósio Brasileiro de Informática na Educação, Blumenau, n.1, 2007.

WOS. Trust the Difference. Web of Science Fact Book, 2021. Disponível em: <https://www.webofknowledge.com>. Acesso em: 09 mar. 2021.

XU, C. W. Learning Java with Games. 2.ed. New York: Springer, 2018.

ZHENYA, H.; Chengjian, W.; Luxi Y.; Xiqi G.; Susu Y. Extracting rules from fuzzy neural network by particle swarm optimisation, IEEE, p. 74-77. 1998. Acesso em: 09 mar. 2021.

ZSOLT, L. K. Redes Neurais Artificiais: fundamentos e aplicações. São Paulo: Livraria da física, 2002.

Additional Files

Published

2022-02-03

How to Cite

Almeida, A. P. C. R., & Alves Nakajima, E. (2022). particle swarm applied to a neural network as backpropagation for optimizing game time . Revista Brasileira De Iniciação Científica, 8, e021050. Retrieved from https://periodicoscientificos.itp.ifsp.edu.br/index.php/rbic/article/view/420

Issue

Volume 8, 2021 – publicação Contínua

Section

Artigos

License

Copyright (c) 2022 Revista Brasileira de Iniciação Científica

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.