Journal article · 2018 · Open access

Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks

Tobias Hinz, Nicolás Navarro-Guerrero, Sven Magg, Stefan Wermter

International Journal of Computational Intelligence and Applications, 17(02), 1850008 · Published 1 June 2018 · DOI 10.1142/s1469026818500086

Open full textCite this paper

In brief

“Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks” is a 2018 journal article by Tobias Hinz and 3 co-authors, published in International Journal of Computational Intelligence and Applications. OpenAlex counts 150 citations as of 20 November 2026, which puts it in the top 4% of works published in 2018 by citations. It is open access under a CC BY licence: the full text is free to read at International Journal of Computational Intelligence and Applications.

Citations
150
Most cited in
2020 (26)
Field-weighted impact
7.62
References
44
Authors
4

Abstract

Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms.

Cite this paper

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

APA 7

Hinz, T., Navarro-Guerrero, N., Magg, S., & Wermter, S. (2018). Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks. International Journal of Computational Intelligence and Applications, 17(02), 1850008. https://doi.org/10.1142/s1469026818500086

MLA 9

Hinz, Tobias, et al. “Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks.” International Journal of Computational Intelligence and Applications, vol. 17, no. 02, 2018, p. 1850008. https://doi.org/10.1142/s1469026818500086.

Chicago

Hinz, Tobias, Nicolás Navarro-Guerrero, Sven Magg, and Stefan Wermter. 2018. “Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks.” International Journal of Computational Intelligence and Applications 17 (02): 1850008. https://doi.org/10.1142/s1469026818500086.

Harvard

Hinz, T. et al. (2018) ‘Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks’, International Journal of Computational Intelligence and Applications, 17(02), p. 1850008. doi:10.1142/s1469026818500086.

IEEE

T. Hinz, N. Navarro-Guerrero, S. Magg, and S. Wermter, “Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks,” International Journal of Computational Intelligence and Applications, vol. 17, no. 02, p. 1850008, 2018, doi: 10.1142/s1469026818500086.

BibTeX

@article{hinz2018speeding,
  title     = {{Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks}},
  author    = {Hinz, Tobias and Navarro-Guerrero, Nicolás and Magg, Sven and Wermter, Stefan},
  journal   = {International Journal of Computational Intelligence and Applications},
  year      = {2018},
  volume    = {17},
  number    = {02},
  pages     = {1850008},
  doi       = {10.1142/s1469026818500086},
  url       = {https://doi.org/10.1142/s1469026818500086}
}

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

Citations by year

YearCitationsShare of the best year
201411
201833
20192222
20202626
20212020
20222424
20232222
20241616
202588
202688

Its field-weighted citation impact is 7.62: it has been cited 7.62 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 › Machine Learning and Data Classification

  • hyperparameter optimization
  • deep convolutional neural networks
  • dimensionality reduction
  • Smac/DIABLO
  • genetic algorithm
  • random search
  • computational efficiency

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?

Hinz, T., Navarro-Guerrero, N., Magg, S., & Wermter, S. (2018). Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks. International Journal of Computational Intelligence and Applications, 17(02), 1850008. https://doi.org/10.1142/s1469026818500086

How many times has this paper been cited?

150 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 International Journal of Computational Intelligence and Applications: sign in and open the full text from this page.

Who wrote this paper?

Tobias Hinz, Nicolás Navarro-Guerrero, Sven Magg, Stefan Wermter.

What is the DOI of this paper?

10.1142/s1469026818500086, permanently at https://doi.org/10.1142/s1469026818500086. 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.