In Evolutionary Artificial Neural Networks (EANN), evolutionary algorithms are used to give an additional alternative to adapt besides learning, specially for connection weights training and architecture design, among others. A type of EANNs known as Topology and Weight Evolving Artificial Neural Networks (TWEANN) are used to evolve topology and weights. In this work, we introduce a new encoding on an implementation of NeuroEvolution of Augmenting Topologies (NEAT), a type of TWEANN, by adopting the Red-Black Tree (RBT) as the main data structure to store the connection genes instead of using a list. This new version of NEAT efficacy was tested using as case of study some data sets from the UCI database. The accuracy of networks obtained through the new version of NEAT were compared with the accuracy obtained from feed-forward artificial neural networks trained using back-propagation. These comparisons yielded that the accuracy were similar, and in some cases the accuracy obtained by the new version were better. Also, as the number of patterns increases, the average number of generations increases exponentially. Finally, there is no relationship between the number of attributes and the number of generations.
- Red-black tree
This is a preview of subscription content, access via your institution.
Tax calculation will be finalised at checkout
Purchases are for personal use onlyLearn about institutional subscriptions
Source code available at https://github.com/cptrodolfox/rbtneat.
Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. The MIT Press, Cambridge (2009)
Floreano, D., Du, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1(1), 47–62 (2008)
Hansapani Rodrigo, C.P.T.: Artificial neural network model for predicting lung cancer survival. J. Data Anal. Inf. Process. 5, 33–47 (2017)
Holland, J.H.: Adaptation in Natural and Artificial Systems, 1st edn. University of Michigan Press, Ann Arbor (1975)
Hunter, D., Yu, H., Pukish III, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures-a comparative study. IEEE Trans. Industr. Inf. 8(2), 228–240 (2012). https://doi.org/10.1109/TII.2012.2187914
Kassahun, Y., Sommer, G.: Efficient reinforcement learning through evolutionary adquisition of neural topologies. In: Proceedings of the 13th Annual European Symposium on Artificial Neural Networks, ESANN. d-side Publishing, Bruges, April 2005
Saman Mohammadi, M.S.: Application of artificial neural networks in order to predict mahabad river discharge. Open J. Ecol. 6, 427–434 (2016)
Stanley, K.O., D’Ambrosio, D., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life J. 15(2), 185–212 (2009)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10, 99–127 (2002)
Vincenzo Pacelli, M.A.: An artificial neural network approach for credit risk management. J. Intell. Learn. Syst. Appl. 3, 103–112 (2011)
Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
The authors acknowledge support through grant TIN2017-88728-C2-1-R from MICINN (Spain) that includes FEDER funds and from Plan Propio from Universidad de Málaga (Spain) and the Yachay Tech University (Ecuador).
Editors and Affiliations
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Arellano, W.R., Silva, P.A., Molina, M.F., Ronquillo, S., Ortega-Zamorano, F. (2019). Red-Black Tree Based NeuroEvolution of Augmenting Topologies. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science(), vol 11507. Springer, Cham. https://doi.org/10.1007/978-3-030-20518-8_56
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20517-1
Online ISBN: 978-3-030-20518-8