Fine-Tuning Restricted Boltzmann Machines Using No-Boundary Jellyfish

Douglas Rodrigues, Gustavo Henrique de Rosa, Kelton Pontara da Costa, Danilo Jodas, João Papa

2023

Abstract

Metaheuristic algorithms present elegant solutions to many problems regardless of their domain. The Jellyfish Search (JS) algorithm is inspired by how jellyfish searches for food in ocean currents and performs movements within the swarm. In this work, we propose a new version of the JS algorithm called No-Boundary Jellyfish Search (NBJS) to improve the convergence rate. The NBJS was applied to fine-tune a Restricted Boltzmann Machine (RBM) in the context of image reconstruction. For validating the proposal, the experiments were carried out on three public datasets to compare the performance of the NBJS algorithm with its original version and two other metaheuristic algorithms. The results showed that proposed approach is viable, for it obtained similar or even lower errors compared to models trained without fine-tuning.

Paper Citation

in Harvard Style

Rodrigues D., Henrique de Rosa G., Pontara da Costa K., Jodas D. and Papa J. (2023). Fine-Tuning Restricted Boltzmann Machines Using No-Boundary Jellyfish. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 65-73. DOI: 10.5220/0011643400003417

in Bibtex Style

@conference{visapp23,
author={Douglas Rodrigues and Gustavo Henrique de Rosa and Kelton Pontara da Costa and Danilo Jodas and João Papa},
title={Fine-Tuning Restricted Boltzmann Machines Using No-Boundary Jellyfish},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={65-73},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011643400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Fine-Tuning Restricted Boltzmann Machines Using No-Boundary Jellyfish
SN - 978-989-758-634-7
AU - Rodrigues D.
AU - Henrique de Rosa G.
AU - Pontara da Costa K.
AU - Jodas D.
AU - Papa J.
PY - 2023
SP - 65
EP - 73
DO - 10.5220/0011643400003417
PB - SciTePress