Authors: Matijević, Luka 
Affiliations: Computer Science 
Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: UTILIZING METAHEURISTICS TO GUIDE THE TRAINING OF NEURAL NETWORKS
First page: 1057
Last page: 1062
Related Publication(s): Zbornik radova
Conference: SYM-OP-IS 2023, Tara, 18-21. septembar 2023.
Issue Date: 2023
Rank: M33
ISBN: 978-86-335-0836-0
URL: https://www.mi.sanu.ac.rs/~luka/resources/papers/UTILIZING_METAHEURISTICS_TO_GUIDE_THE_TRAINING_OF_NEURAL_NETWORKS.pdf
Abstract: 
Neural networks (NN), have become increasingly popular due to their practical
applications. NN training is a crucial stage in constructing a reliable model that can accurately
predict data. The goal of NN training is to determine the best internal parameters to optimize the
network's performance on test data, according to a specific metric. In this study, we explore the use
of metaheuristics to guide the entire training process. Our approach involves identifying favorable
areas of the search space and invoking an optimizer to intensify the search in these regions. To
train NN, we implemented two metaheuristics, Variable Neighborhood Search (VNS) and the
Memetic algorithm (MA), and measured their effectiveness using classification accuracy as an
evaluation metric on publicly available classification datasets. The obtained results suggest that
MA is able to outperform both VNS and traditional training methods.
Keywords: Machine Learning | Combinatorial Optimization | Classification Accuracy | Variable Neighborhood Search | Memetic Algorithm
Publisher: Medija centar "Odbrana"
Project: This work was supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia, Agreement No. 451-03-47/2023-01/200029

Show full item record

Page view(s)

19
checked on Apr 16, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.