TY - JOUR
T1 - Logic-driven autoencoders
AU - Al-Hmouz, Rami
AU - Pedrycz, Witold
AU - Balamash, Abdullah
AU - Morfeq, Ali
N1 - Funding Information:
This project was funded by the Deanship of Scientific Research (DSR) , King Abdulaziz University, Jeddah, Saudi Arabia under grant no. (KEP-5-135-39) . The authors, therefore, acknowledge with thanks DSR technical and financial support.
Funding Information:
This project was funded by the Deanship of Scientific Research (DSR), King Abdulaziz University, Jeddah, Saudi Arabia under grant no. (KEP-5-135-39). The authors, therefore, acknowledge with thanks DSR technical and financial support.
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/11/1
Y1 - 2019/11/1
N2 - 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.
AB - 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.
KW - AND neurons
KW - Autoencoder
KW - Deep learning
KW - Fuzzy neurons
KW - Knowledge representation
KW - Learning
KW - Logic processing
KW - OR neurons
UR - http://www.scopus.com/inward/record.url?scp=85070212527&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070212527&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2019.104874
DO - 10.1016/j.knosys.2019.104874
M3 - Article
AN - SCOPUS:85070212527
SN - 0950-7051
VL - 183
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 104874
ER -