A Metaheuristic-Driven Approach to Fine-Tune Deep Boltzmann Machines
This work addresses hyperparameter tuning for DBMs, which is an incremental improvement for researchers in deep learning.
The paper tackled the problem of fine-tuning hyperparameters in Deep Boltzmann Machines by using metaheuristic optimization techniques, and experiments on three public datasets for binary image reconstruction showed that these techniques can achieve reasonable results.
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.