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

arXiv: https://arxiv.org/abs/2101.05795 · HTML: https://mlsanity.com/paper/2101.05795/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 51 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 2 of 2)

- [Temperature-Based Deep Boltzmann Machines](https://mlsanity.com/paper/1608.07719/) (2016)
- [LibOPT: An Open-Source Platform for Fast Prototyping Soft Optimization Techniques](https://mlsanity.com/paper/1704.05174/) (2017)

## Built on by (most cited first, 2 of 2)

- [PL-kNN: A Parameterless Nearest Neighbors Classifier](https://mlsanity.com/paper/2209.12647/) (2022)
- [A Layer-Wise Information Reinforcement Approach to Improve Learning in Deep Belief Networks](https://mlsanity.com/paper/2101.06749/) (2021)

## Abstract (arXiv)

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.