Granular autoencoders: concepts and design

Witold Pedrycz, Rami Al-Hmouz*, Abdullah Balamash, Ali Morfeq

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Autoencoders are regarded as one of the key functional components of deep learning architectures. In this study, we augment the well-known architectures of autoencoders by incorporating a concept of information granularity, which gives rise to so-called granular autoencoders. It is demonstrated that information granularity can be sought as an essential design asset whose optimal allocation produces the autoencoder with better representation capabilities. Several protocols of allocation of information granularity are presented and assessed with regard to their abilities to represent the data. Selected examples including those dealing with clustering time series are included.

Original languageEnglish
Pages (from-to)9869-9880
Number of pages12
JournalSoft Computing
Volume23
Issue number20
DOIs
Publication statusPublished - Oct 1 2019
Externally publishedYes

Keywords

  • Autoencoders
  • Deep learning
  • Granular computing
  • Information granularity and its optimal allocation

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Geometry and Topology

Fingerprint

Dive into the research topics of 'Granular autoencoders: concepts and design'. Together they form a unique fingerprint.

Cite this