A metaheuristic-driven approach to fine-tune Deep Boltzmann Machines

• Autor(a) principal: Passos, Leandro Aparecido
• Data de Publicação: 2020
• Outros Autores: Papa, Joao Paulo [UNESP]
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1016/j.asoc.2019.105717; http://hdl.handle.net/11449/209831
• topic: Deep Boltzmann Machine; Meta-heuristic optimization; Machine learning

Deep learning techniques, such as Deep Boltzmann Machines (DBMs), have received considerable attention over the past years due to the outstanding results concerning a variable range of domains. One of the main shortcomings of these techniques involves the choice of their hyperparameters, since they have a significant impact on the final results. This work addresses the issue of fine-tuning hyperparameters of Deep Boltzmann Machines using metaheuristic optimization techniques with different backgrounds, such as swarm intelligence, memoryand evolutionary-based approaches. Experiments conducted in three public datasets for binary image reconstruction showed that metaheuristic techniques can obtain reasonable results. (C) 2019 Elsevier B.V. All rights reserved.