Influence of hidden neuron number on the performance of ANN models applied to deinking flotation data
Loading...
Date
2025
Authors
Balanović, Katarina
Trumić, Maja
Gavrilović, Tamara
Journal Title
Journal ISSN
Volume Title
Publisher
University of Belgrade - Technical Faculty in Bor
Source
Proceedings [Elektronski izvor] - 56th International October Conference on Mining and Metallurgy - IOC 2025, 22-25 October, 2025, Bor Lake, Serbia
Volume
Issue
Abstract
In this paper, the influence of the optimal number of neurons in an artificial neural network model, applied to data obtained from deinking flotation is presented and analyzed. The results indicate that when a wellperforming model is selected, it is not necessary to search for the optimal number of hidden neurons. However, when the applied model does not yield satisfactory results, determining the optimal number of neurons becomes essential.
Description
Keywords
Artificial neural networks, Hidden neurons, Flotation, Deinking
Citation
DOI
10.5937/IOC25229B
Scopus
ISSN
ISBN
978-86-6305-164-5
License
CC-BY-NC-ND