Abstract
The paper presents an idea of training an artificial neural network a relation between different parameters observed for a population in a metaheuristic algorithm. Then such trained network may be used for controlling other algorithms (if the network is trained in such way, that the knowledge gathered by it becomes agnostic regarding the problem). The paper focuses on showing the idea and also provides selected experimental results obtained after applying the proposed algorithm for solving popular benchmark problems in different dimensions.
The research presented in this paper has been financially supported by: Polish National Science Center Grant no. 2019/35/O/ST6/00570 “Socio-cognitive inspirations in classic metaheuristics.” (A.U.) and Polish Ministry of Education and Science funds assigned to AGH University of Science and Technology (T.P-P., M.K-D., A.B.).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/, software available from tensorflow.org
Aine, S., Kumar, R., Chakrabarti, P.P.: Adaptive parameter control of evolutionary algorithms under time constraints. In: Tiwari, A., Roy, R., Knowles, J., Avineri, E., Dahal, K. (eds.) Applications of Soft Computing. AISC, vol. 36, pp. 373–382. Springer, Heidelberg (2006). https://doi.org/10.1007/978-3-540-36266-1_36
Auger, A., Le Bris, C., Schoenauer, M.: Dimension-independent convergence rate for non-isotropic (1, \(\lambda \)) — ES. In: Cantú-Paz, E., et al. (eds.) GECCO 2003, Part I. LNCS, vol. 2723, pp. 512–524. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-45105-6_64
Bäck, T., Eiben, A.E., van der Vaart, N.A.L.: An emperical study on GAs “without parameters’’. In: Schoenauer, M., et al. (eds.) PPSN 2000. LNCS, vol. 1917, pp. 315–324. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45356-3_31
Bassin, A., Buzdalov, M.: The 1/5-th rule with rollbacks. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, July 2019. https://doi.org/10.1145/3319619.3322067. http://dx.doi.org/10.1145/3319619.3322067
Benidis, K., et al.: Neural forecasting: introduction and literature overview. https://arxiv.org/abs/2004.10240 (2020)
Benítez-Hidalgo, A., Nebro, A.J., García-Nieto, J., Oregi, I., Del Ser, J.: jMetalPY: a python framework for multi-objective optimization with metaheuristics. Swarm Evol. Comput. 51, 100598 (2019). https://doi.org/10.1016/j.swevo.2019.100598. https://www.sciencedirect.com/science/article/pii/S2210650219301397
Botalb, A., Moinuddin, M., Al-Saggaf, U.M., Ali, S.S.A.: Contrasting Convolutional Neural Network (CNN) with Multi-Layer Perceptron (MLP) for big data analysis. In: 2018 International Conference on Intelligent and Advanced System (ICIAS), pp. 1–5 (2018). https://doi.org/10.1109/ICIAS.2018.8540626
Bäck, T.: Self-adaptation in genetic algorithms. In: Proceedings of the First European Conference on Artificial Life, pp. 263–271. MIT Press (1992)
Corriveau, G., Guilbault, R., Tahan, A., Sabourin, R.: Bayesian network as an adaptive parameter setting approach for genetic algorithms. Complex Intell. Syst. 2(1), 1–22 (2016). https://doi.org/10.1007/s40747-016-0010-z
Deb, K., Agrawal, R.B., et al.: Simulated binary crossover for continuous search space. Complex Syst. 9(2), 115–148 (1995)
Digalakis, J., Margaritis, K.: An experimental study of benchmarking functions for evolutionary algorithms. Int. J. Comput. Math. 79, 403–416 (2002)
Eiben, A., Smit, S.: Parameter tuning for configuring and analyzing evolutionary algorithms. Swarm Evol. Comput. 1, 19–31 (2011). https://doi.org/10.1016/j.swevo.2011.02.001
Eiben, A.E., Smith, J.E., Michalewicz, Z., Schoenauer, M., Smith, J.E.: Parameter control in evolutionary algorithms. Stud. Comput. Intell. 54, 19–46 (2007)
Gomes Pereira De Lacerda, M., Filipe De Araujo Pessoa, L., Buarque De Lima Neto, F., Ludermir, T.B., Kuchen, H.: A systematic literature review on general parameter control for evolutionary and swarm-based algorithms. Swarm Evol. Comput. 60, 100777 (2021). https://doi.org/10.1016/j.swevo.2020.100777. www.elsevier.com/locate/swevo
Hansen, N., Ostermeier, A.: Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation. In: Proceedings of IEEE International Conference on Evolutionary Computation, pp. 312–317 (1996). https://doi.org/10.1109/ICEC.1996.542381
Karafotias, G., Hoogendoorn, M., Eiben, A.E.: Parameter control in evolutionary algorithms: trends and challenges. IEEE Trans. Evol. Comput. 19(2), 167–187 (2015). https://doi.org/10.1109/TEVC.2014.2308294
Maturana, J., Saubion, F.: On the design of adaptive control strategies for evolutionary algorithms. In: Monmarché, N., Talbi, E.-G., Collet, P., Schoenauer, M., Lutton, E. (eds.) EA 2007. LNCS, vol. 4926, pp. 303–315. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-79305-2_26
McGinley, B., Maher, J., O’Riordan, C., Morgan, F.: Maintaining healthy population diversity using adaptive crossover, mutation, and selection. IEEE Trans. Evol. Comput. 15(5), 692–714 (2011)
Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs. Springer, Heidelberg (1996). https://doi.org/10.1007/978-3-662-03315-9
Morrison, R., De Jong, K.: Measurement of population diversity, vol. 2310, pp. 31–41, October 2001
Narendra, K.S., Parthasarathy, K.: Neural networks and dynamical systems. Int. J. Approx. Reason. 6(2), 109–131 (1992). https://doi.org/10.1016/0888-613X(92)90014-Q
Paternain, S., Morari, M., Ribeiro, A.: Real-time model predictive control based on prediction-correction algorithms. In: 2019 IEEE 58th Conference on Decision and Control (CDC), pp. 5285–5291. IEEE (2019). https://doi.org/10.1109/CDC40024.2019.9029408
Sammut, C., Webb, G.I. (eds.): Mean Squared Error, p. 653. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-30164-8
Schumer, M., Steiglitz, K.: Adaptive step size random search. Autom. Contr. IEEE Trans. AC13, 270–276 (1968). https://doi.org/10.1109/TAC.1968.1098903
Schwefel, H.P.: Numerical Optimization of Computer Models. Wiley, New York (1981)
Shiblee, M., Kalra, P.K., Chandra, B.: Time series prediction with multilayer perceptron (MLP): a new generalized error based approach. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008. LNCS, vol. 5507, pp. 37–44. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03040-6_5
Smit, S.K., Eiben, A.E.: Comparing parameter tuning methods for evolutionary algorithms. In: 2009 IEEE Congress on Evolutionary Computation, pp. 399–406. IEEE (2009)
Wang, J., Li, X., Li, J., Sun, Q., Wang, H.: NGCU: a new RNN model for time-series data prediction. Big Data Res. 27, 100296 (2022). https://doi.org/10.1016/j.bdr.2021.100296
Werbos, P.J.: Consistency of HDP applied to a simple reinforcement learning problem. Neural Netw. 3(2), 179–189 (1990). https://doi.org/10.1016/0893-6080(90)90088-3
Zhu, K.Q., Liu, Z.: Population diversity in permutation-based genetic algorithm. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 537–547. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30115-8_49
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dobrzański, T., Urbańczyk, A., Pełech-Pilichowski, T., Kisiel-Dorohinicki, M., Byrski, A. (2022). Neural-Network Based Adaptation of Variation Operators’ Parameters for Metaheuristics. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13351. Springer, Cham. https://doi.org/10.1007/978-3-031-08754-7_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-08754-7_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08753-0
Online ISBN: 978-3-031-08754-7
eBook Packages: Computer ScienceComputer Science (R0)