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

Abstract

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.

Sašo Pavlič

PhD student in computer science & informatics

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