Momentum Enhanced Neuroevolution
Keywords
DXNN; Evolutionary computation; Genetic algorithm; Memetic Algorithm; Momentum parameter; Neural network; Neuroevolution
Abstract
The momentum parameter is common within numerous optimization and local search algorithms, particularly in the popular back propagation neural network learning algorithm. Computationally cheap and prevalent in gradient descent approaches, it is not currently utilized within neuroevolution. In this paper we present some of the results produced by a momentum enhanced neuroevolutionary algorithm. We demonstrate how this computationally inexpensive parameter in most of the cases results in enhancing the system's performance.
Publication Date
7-11-2015
Publication Title
GECCO 2015 - Companion Publication of the 2015 Genetic and Evolutionary Computation Conference
Number of Pages
1483-1484
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/2739482.2764709
Copyright Status
Unknown
Socpus ID
84959422228 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84959422228
STARS Citation
Sher, Gene, "Momentum Enhanced Neuroevolution" (2015). Scopus Export 2015-2019. 1800.
https://stars.library.ucf.edu/scopus2015/1800