EUVIMEDOpdag EUVIMED
Open access · CC BY-NC 4.0

Swish‐Gumbel: A New Activation Function for Image Classification

Elif Dorukbaşı, Burhan Selçuk, İlker Türker

Concurrency and Computation: Practice and Experience · 2026-07 · 38 (14)

DOI: 10.1002/cpe.70822 ↗

At a glance

Journal article in Concurrency and Computation: Practice and Experience, published online on 2026-07-14. Written by Elif Dorukbaşı and 2 co-authors. 42 references. The full text is freely available (open access, CC BY-NC 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

In this study, we present Swish‐Gumbel, a new family of activation functions generated by combining the Swish and Gumbel functions through both multiplication and linear composition. We evaluate their performance on several image classification benchmarks, including MNIST, CIFAR‐10, Imagenette, and Beans, using different deep learning architectures. The results show that the multiplicative version consistently outperforms well‐known activation functions such as ReLU, Swish, Mish, and Gumbel, while the linear combination variants provide competitive results particularly on simpler datasets, with performance gains becoming more pronounced for the multiplicative form on complex benchmarks. The strength of the proposed approach lies in its ability to maintain more stable gradients in the positive domain, which improves feature extraction and generalization. Overall, our findings suggest that Swish‐Gumbel can serve as an effective alternative to existing activation functions for image classification, with potential to be applied in other machine learning tasks as well.

Cite

APA

Dorukbaşı, E., Selçuk, B., & Türker, İ. (2026). Swish‐Gumbel: A New Activation Function for Image Classification. Concurrency and Computation: Practice and Experience, 38(14). https://doi.org/10.1002/cpe.70822

Vancouver

Dorukbaşı E, Selçuk B, Türker İ. Swish‐Gumbel: A New Activation Function for Image Classification. Concurrency and Computation: Practice and Experience. 2026;38(14). doi:10.1002/cpe.70822

BibTeX
@article{Dorukba2026,
  author = {Dorukbaşı, Elif and Selçuk, Burhan and Türker, İlker},
  title = {Swish‐Gumbel: A New Activation Function for Image Classification},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {14},
  doi = {10.1002/cpe.70822}
}
Start for free →