Logic-driven autoencoders

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

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

Autoencoders are computing architectures encountered in various schemes of deep learning and realizing an efficient way of representing data in a compact way by forming a set of features. In this study, a concept, architecture, and algorithmic developments of logic-driven autoencoders are presented. In such structures, encoding and the decoding processes realized at the consecutive layers of the autoencoder are completed with the aid of some fuzzy logic operators (namely, OR, AND, NOT operations) and the ensuing encoding and decoding processing is carried out with the aid of fuzzy logic processing. The optimization of the autoencoder is completed through a gradient-based learning. The transparent knowledge representation delivered by autoencoders is facilitated by the involvement of logic processing, which implies that the encoding mechanism comes with the generalization abilities delivered by OR neurons while the specialization mechanism is achieved by the AND-like neurons forming the decoding layer. A series of illustrative examples is also presented.

Original languageEnglish
Article number104874
JournalKnowledge-Based Systems
Volume183
DOIs
Publication statusPublished - Nov 1 2019
Externally publishedYes

Keywords

  • AND neurons
  • Autoencoder
  • Deep learning
  • Fuzzy neurons
  • Knowledge representation
  • Learning
  • Logic processing
  • OR neurons

ASJC Scopus subject areas

  • Management Information Systems
  • Software
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Logic-driven autoencoders'. Together they form a unique fingerprint.

Cite this