Skip to Main content Skip to Navigation
New interface
Book sections

Evolving Developmental Programs That Build Neural Networks for Solving Multiple Problems

Abstract : A developmental model of an artificial neuron is presented. In this model, a pair of neural developmental programs develop an entire artificial neural network of arbitrary size. The pair of neural chromosomes are evolved using Cartesian Genetic Programming. During development, neurons and their connections can move, change, die or be created. We show that this two-chromosome genotype can be evolved to develop into a single neural network from which multiple conventional artificial neural networks can be extracted. The extracted conventional ANNs share some neurons across tasks. We have evaluated the performance of this method on three standard classification problems: cancer, diabetes and the glass datasets. The evolved pair of neuron programs can generate artificial neural networks that perform reasonably well on all three benchmark problems simultaneously. It appears to be the first attempt to solve multiple standard classification problems using a developmental approach.
Document type :
Book sections
Complete list of metadata
Contributor : Françoise Grélaud Connect in order to contact the contributor
Submitted on : Friday, October 23, 2020 - 2:57:29 PM
Last modification on : Monday, July 4, 2022 - 10:07:01 AM


  • HAL Id : hal-02976648, version 1


Julian Miller, Dennis G. Wilson, Sylvain Cussat-Blanc. Evolving Developmental Programs That Build Neural Networks for Solving Multiple Problems. Banzhaf; Wolfgang and Spector; Lee and Sheneman; Leigh. Genetic Programming Theory and Practice XVI, Springer, pp.137--178, 2019, GEVO : Genetic and Evolutionary Computation book series, 978-3-030-04734-4. ⟨hal-02976648⟩



Record views