A Metaheuristic-Driven Approach to Fine-Tune Deep Boltzmann Machines

TL;DR

This paper presents a metaheuristic-driven method to optimize hyperparameters of Deep Boltzmann Machines, improving their performance in binary image reconstruction tasks.

Contribution

It introduces a novel approach combining various metaheuristic algorithms for fine-tuning DBM hyperparameters, addressing a key challenge in deep learning.

Findings

Metaheuristic techniques achieve reasonable hyperparameter optimization results.

Experiments on three datasets demonstrate improved image reconstruction.

Different metaheuristics show comparable effectiveness.

Abstract

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, memory- and evolutionary-based approaches. Experiments conducted in three public datasets for binary image reconstruction showed that metaheuristic techniques can obtain reasonable results.