Please note that UPSpace will be offline from 20:00 on 9 May to 06:00 on 10 May (SAST) due to maintenance. We apologise for any inconvenience caused by this.
 

Neural network crossover in genetic algorithms using genetic programming

Loading...
Thumbnail Image

Authors

Pretorius, Kyle
Pillay, Nelishia

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

The use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from such GAs as they are seen as being highly destructive and detrimental to the performance of the GA. Designing crossover operators that can effectively be applied to NNs has been an active area of research with success limited to specific problem domains. The focus of this study is to use genetic programming (GP) to automatically evolve crossover operators that can be applied to NN weights and used in GAs. A novel GP is proposed and used to evolve both reusable and disposable crossover operators to compare their efficiency. Experiments are conducted to compare the performance of GAs using no crossover operator or a commonly used human designed crossover operator to GAs using GP evolved crossover operators. Results from experiments conducted show that using GP to evolve disposable crossover operators leads to highly effectively crossover operators that significantly improve the results obtained from the GA.

Description

Keywords

Genetic algorithm (GA), Neural network, Genetic programming, Evolutionary algorithms, Crossover operator, SDG-09: Industry, innovation and infrastructure

Sustainable Development Goals

SDG-09: Industry, innovation and infrastructure

Citation

Pretorius, K., Pillay, N. Neural network crossover in genetic algorithms using genetic programming. Genetic Programming and Evolvable Machines 25, 7 (2024). https://doi.org/10.1007/s10710-024-09481-7.