Behavior-based Speciation in Classification with NeuroEvolution

Research output: Chapter in Book/Report/Conference proceedingConference paper


We propose a neuroevolutionary speciation mechanism that is applied on NeuroEvolution of Augmenting Topologies (NEAT) that solely evolves neural networks’ topology and weights and its extension HA-NEAT that also evolves activation functions. The new speciation mechanism is defined based on the behavior of the individuals rather than their topological similarity. Focusing on classification tasks we build artificial datasets of high complexity. Performance is described by (i) median classification accuracy, (ii) computational efficiency (number of generations) and (iii) network complexity (number of nodes and connections). The performance metrics are compared using Kruskal-Wallis hypothesis tests with Bonferroni correction. It is found that the proposed behavioral speciation mechanism outperforms the original speciation solving problems that were not solvable before or improving the accuracy and reducing the network complexity
Original languageEnglish
Title of host publication2020 IEEE World Congress on Computational Intelligence
Subtitle of host publication2020 IEEE Congress on Evolutionary Computation (CEC)
Number of pages7
ISBN (Electronic)978-1-7281-6929-3
Publication statusPublished - Jul 2020
Event2020 IEEE World Congress on Computational Intelligence : 2020 IEEE Congress on Evolutionary Computation (CEC) - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

Name2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings


Conference2020 IEEE World Congress on Computational Intelligence
Abbreviated titleIEEE WCCI 2020
CountryUnited Kingdom

Fingerprint Dive into the research topics of 'Behavior-based Speciation in Classification with NeuroEvolution'. Together they form a unique fingerprint.

Cite this