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

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.

30 pages, 7 figures

Cited by in corpus (2)

• PL-kNN: A Parameterless Nearest Neighbors Classifier
• A Layer-Wise Information Reinforcement Approach to Improve Learning in Deep Belief Networks