NiaNet: A framework for constructing Autoencoder architectures using nature-inspired algorithms

• Autorzy: Pavlič Sašo , Fister Jr. Iztok , Karakatič Sašo

Identyfikatory

DOI

10.15439/2022F192

• Języki publikacji: EN

Abstrakty

EN

Autoencoder, an hourly glass-shaped deep neural network capable of learning data representation in a lower dimension, has performed well in various applications. However, developing a high-quality AE system for a specific task heavily relies on human expertise, limiting its widespread application. On the other hand, there has been a gradual increase in automated machine learning for developing deep learning systems without human intervention. However, there is a shortage of automatically designing particular deep neural networks such as AE. This study presents the NiaNet method and corresponding software framework for designing AE topology and hyper-parameter settings. Our findings show that it is possible to discover the optimal AE architecture for a specific dataset without the requirement for human expert assistance. The future potential of the proposed method is also discussed in this paper.

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 30
• Strony: 109--116
• Opis fizyczny: Bibliogr. 38 poz.

Twórcy

autor

Pavlič Sašo

autor

Fister Jr. Iztok

autor

Karakatič Sašo