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


Autoencoder, an hourly glass-shaped deep neuralnetwork 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.

Annals of Computer Science and Information Systems, Volume 30
Sašo Pavlič
Sašo Pavlič
PhD student in computer science & informatics

My research interests include artificial inteligence, machine learning, neural architecture search, anomaly detection, …