Conference paper · 2017 · Open access

Hyper-parameter selection in deep neural networks using parallel particle swarm optimization

Pablo Ribalta Lorenzo, Jakub Nalepa, Luciano Sanchez Ramos, José Ranilla

Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1864–1871 · Published 11 July 2017 · DOI 10.1145/3067695.3084211

Open full textView at the publisherCite this paper

In brief

“Hyper-parameter selection in deep neural networks using parallel particle swarm optimization” is a 2017 conference paper by Pablo Ribalta Lorenzo and 3 co-authors, published in Genetic and Evolutionary Computation Conference Companion (GECCO Companion). OpenAlex counts 94 citations as of 20 November 2026, which puts it in the top 7% of works published in 2017 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Repositorio de la Universidad de Oviedo (RUO).

Citations
94
Most cited in
2021 (20)
Field-weighted impact
3.32
References
24
Authors
4

Abstract

The need of manual hyper-parameter selection can seriously hamper the model optimization of Deep Neural Networks (DNNs). Conventional automated approaches tackling this problem suffer from poor scalability or fail in certain scenarios. In this paper, we introduce a parallel method that applies Particle Swarm Optimization (PSO) for the hyper-parameter selection in DNNs. To estimate the best hyper-parameters, a population of particles is evolved, with their fitness calculated in parallel. The experimental results demonstrate very desirable scalability properties for different DNNs. We show that the parallel PSO can further optimize existent models designed by experts in an affordable amount of time.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Lorenzo, P. R., Nalepa, J., Ramos, L. S., & Ranilla, J. (2017). Hyper-parameter selection in deep neural networks using parallel particle swarm optimization. Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1864–1871. https://doi.org/10.1145/3067695.3084211

MLA 9

Lorenzo, Pablo Ribalta, et al. “Hyper-parameter selection in deep neural networks using parallel particle swarm optimization.” Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 2017, pp. 1864–1871. https://doi.org/10.1145/3067695.3084211.

Chicago

Lorenzo, Pablo Ribalta, Jakub Nalepa, Luciano Sanchez Ramos, and José Ranilla. 2017. “Hyper-parameter selection in deep neural networks using parallel particle swarm optimization.” Genetic and Evolutionary Computation Conference Companion (GECCO Companion): 1864–1871. https://doi.org/10.1145/3067695.3084211.

Harvard

Lorenzo, P. R. et al. (2017) ‘Hyper-parameter selection in deep neural networks using parallel particle swarm optimization’, Genetic and Evolutionary Computation Conference Companion (GECCO Companion), pp. 1864–1871. doi:10.1145/3067695.3084211.

IEEE

P. R. Lorenzo, J. Nalepa, L. S. Ramos, and J. Ranilla, “Hyper-parameter selection in deep neural networks using parallel particle swarm optimization,” Genetic and Evolutionary Computation Conference Companion (GECCO Companion), pp. 1864–1871, 2017, doi: 10.1145/3067695.3084211.

BibTeX

@inproceedings{lorenzo2017hyper,
  title     = {{Hyper-parameter selection in deep neural networks using parallel particle swarm optimization}},
  author    = {Lorenzo, Pablo Ribalta and Nalepa, Jakub and Ramos, Luciano Sanchez and Ranilla, José},
  booktitle = {Genetic and Evolutionary Computation Conference Companion (GECCO Companion)},
  year      = {2017},
  pages     = {1864--1871},
  doi       = {10.1145/3067695.3084211},
  url       = {https://doi.org/10.1145/3067695.3084211}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201722
201844
20191616
20201212
20212020
20221515
202377
202477
202577
202644

Its field-weighted citation impact is 3.32: it has been cited 3.32 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research

  • hyperparameter optimization
  • deep neural network
  • particle swarm optimization
  • parallel optimization
  • automated machine learning
  • scalability
  • model optimization

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Lorenzo, P. R., Nalepa, J., Ramos, L. S., & Ranilla, J. (2017). Hyper-parameter selection in deep neural networks using parallel particle swarm optimization. Genetic and Evolutionary Computation Conference Companion (GECCO Companion), 1864–1871. https://doi.org/10.1145/3067695.3084211

How many times has this paper been cited?

94 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Repositorio de la Universidad de Oviedo (RUO): sign in and open the full text from this page.

Who wrote this paper?

Pablo Ribalta Lorenzo, Jakub Nalepa, Luciano Sanchez Ramos, José Ranilla.

What is the DOI of this paper?

10.1145/3067695.3084211, permanently at https://doi.org/10.1145/3067695.3084211. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.