Abstract

Neural networks have achieved in recent years human level performance in various application domains, including critical applications where accountability is a very important issue, closely related to the interpretability of neural networks and artificial intelligence in general. In this work, an approach for defining the structure of neural networks based on the conceptualisation and semantics of the application domain is proposed. The proposed approach, called Semantic Artificial Neural Networks, allows dealing with the problem of interpretability and also the definition of the structure of neural networks. In addition, the resulting neural networks are sparser and have fewer parameters than typical neural networks, while achieving high performance.
Original languageEnglish
Title of host publicationThe Semantic Web
Subtitle of host publicationESWC 2020 Satellite Events
EditorsAndreas Harth, Valentina Presutti, Raphaël Troncy, Maribel Acosta, Axel Polleres, Javier D. Fernández, Josiane Xavier Parreira, Olaf Hartig, Katja Hose, Michael Cochez
Place of PublicationCham
PublisherSpringer, Cham
Pages39-44
Number of pages6
VolumeLNCS 12124
ISBN (Electronic)9783030623272
ISBN (Print)9783030623265
DOIs
Publication statusPublished - 11 Nov 2020
EventExtended Semantic Web Conference 2020 - Crete, Greece
Duration: 31 May 20204 Jun 2020
https://2020.eswc-conferences.org/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Nature Switzerland AG
VolumeLNCS 12124
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceExtended Semantic Web Conference 2020
Abbreviated titleESWC2020
CountryGreece
CityCrete
Period31/05/204/06/20
OtherVirtual Conference
Internet address

Fingerprint

Dive into the research topics of 'Semantic Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this