Feature Selective Neuroevolution of Augmenting Topologies (FSNEAT) and Feature De-selective Neuroevolution of Augmenting Topologies (FD-NEAT) are two well-known methods for optimizing the topology and the weights of Artificial Neural Networks (ANNs) while simultaneously performing feature selection. Literature has shown that starting the evolution with ANNs of one hidden layer can affect FD-NEAT's and FS-NEAT's performances. However, no study exists that investigates the e.ects of changing the networks' initial connectivity. In this paper we investigate how the choice of the number of initially connected inputs a.ects the performance of FD-NEAT and FS-NEAT in terms of accuracy, number of generations required for convergence, ability of performing feature selection and size of the evolved networks. For this purpose we employ artificial datasets of increasing complexity based on the exclusive-or (XOR) problem with irrelevant features.The di.erent initial topological se.ings are compared using Kruskal-Wallis hypothesis tests with Bonferroni correction (p<0.01), while FD-NEAT and FS-NEAT are compared using Wilcoxon rank sum hypothesis tests (p<0.01).The results show that the initial connectivity se.ing does not affect the performance of FD-NEAT and FS-NEAT.
Papavasileiou, E & Jansen, B 2017, 'An Investigation of Topological Choices in FS-NEAT and FD-NEAT on XOR-based Problems of Increased Complexity', GECCO 2017 Genetic and Evolutionary Computation Conference, Berlin, Belgium, 15/07/17 - 19/07/17 pp. 1431-1434. https://doi.org/10.1145/3067695.3082497
Papavasileiou, E., & Jansen, B. (2017). An Investigation of Topological Choices in FS-NEAT and FD-NEAT on XOR-based Problems of Increased Complexity. 1431-1434. Poster session presented at GECCO 2017 Genetic and Evolutionary Computation Conference, Berlin, Belgium. https://doi.org/10.1145/3067695.3082497
@conference{59bced4039a946fba4e6c0adae238459,
title = "An Investigation of Topological Choices in FS-NEAT and FD-NEAT on XOR-based Problems of Increased Complexity",
abstract = "Feature Selective Neuroevolution of Augmenting Topologies (FSNEAT) and Feature De-selective Neuroevolution of Augmenting Topologies (FD-NEAT) are two well-known methods for optimizing the topology and the weights of Artificial Neural Networks (ANNs) while simultaneously performing feature selection. Literature has shown that starting the evolution with ANNs of one hidden layer can affect FD-NEAT's and FS-NEAT's performances. However, no study exists that investigates the e.ects of changing the networks' initial connectivity. In this paper we investigate how the choice of the number of initially connected inputs a.ects the performance of FD-NEAT and FS-NEAT in terms of accuracy, number of generations required for convergence, ability of performing feature selection and size of the evolved networks. For this purpose we employ artificial datasets of increasing complexity based on the exclusive-or (XOR) problem with irrelevant features.The di.erent initial topological se.ings are compared using Kruskal-Wallis hypothesis tests with Bonferroni correction (p<0.01), while FD-NEAT and FS-NEAT are compared using Wilcoxon rank sum hypothesis tests (p<0.01).The results show that the initial connectivity se.ing does not affect the performance of FD-NEAT and FS-NEAT.",
keywords = "Neuroevolution, Supervised learning, Topology initialization",
author = "Evgenia Papavasileiou and Bart Jansen",
year = "2017",
month = jul,
day = "15",
doi = "10.1145/3067695.3082497",
language = "English",
pages = "1431--1434",
note = "GECCO 2017 Genetic and Evolutionary Computation Conference ; Conference date: 15-07-2017 Through 19-07-2017",
}