Semantic Artificial Neural Networks

Sotirios Batsakis; Ilias Tachmazidis; George Baryannis; Grigoris Antoniou

doi:10.1007/978-3-030-62327-2_7

Semantic Artificial Neural Networks

Sotirios Batsakis, Ilias Tachmazidis, George Baryannis, Grigoris Antoniou

Technical University of Crete

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

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 language	English
Title of host publication	The Semantic Web
Subtitle of host publication	ESWC 2020 Satellite Events
Editors	Andreas Harth, Valentina Presutti, Raphaël Troncy, Maribel Acosta, Axel Polleres, Javier D. Fernández, Josiane Xavier Parreira, Olaf Hartig, Katja Hose, Michael Cochez
Place of Publication	Cham
Publisher	Springer, Cham
Pages	39-44
Number of pages	6
Volume	LNCS 12124
ISBN (Electronic)	9783030623272
ISBN (Print)	9783030623265
DOIs	https://doi.org/10.1007/978-3-030-62327-2_7
Publication status	Published - 11 Nov 2020
Event	Extended Semantic Web Conference 2020 - Crete, Greece Duration: 31 May 2020 → 4 Jun 2020 https://2020.eswc-conferences.org/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Nature Switzerland AG
Volume	LNCS 12124
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Extended Semantic Web Conference 2020
Abbreviated title	ESWC2020
Country/Territory	Greece
City	Crete
Period	31/05/20 → 4/06/20
Other	Virtual Conference
Internet address	https://2020.eswc-conferences.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-030-62327-2_7Licence: Unspecified

paper_291Accepted author manuscript, 144 KBLicence: Unspecified

Cite this

Batsakis, S., Tachmazidis, I., Baryannis, G., & Antoniou, G. (2020). Semantic Artificial Neural Networks. In A. Harth, V. Presutti, R. Troncy, M. Acosta, A. Polleres, J. D. Fernández, J. X. Parreira, O. Hartig, K. Hose, & M. Cochez (Eds.), The Semantic Web: ESWC 2020 Satellite Events (Vol. LNCS 12124, pp. 39-44). (Lecture Notes in Computer Science; Vol. LNCS 12124). Springer, Cham. https://doi.org/10.1007/978-3-030-62327-2_7

Batsakis, Sotirios ; Tachmazidis, Ilias ; Baryannis, George et al. / Semantic Artificial Neural Networks. The Semantic Web: ESWC 2020 Satellite Events. editor / Andreas Harth ; Valentina Presutti ; Raphaël Troncy ; Maribel Acosta ; Axel Polleres ; Javier D. Fernández ; Josiane Xavier Parreira ; Olaf Hartig ; Katja Hose ; Michael Cochez. Vol. LNCS 12124 Cham : Springer, Cham, 2020. pp. 39-44 (Lecture Notes in Computer Science).

@inproceedings{9fdb0a4360374bfdbf63ff72bd474100,

title = "Semantic Artificial Neural Networks",

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.",

keywords = "Semantic Neural Networks, Neural Networks, Artificial intelligence (AI), Machine learning methods",

author = "Sotirios Batsakis and Ilias Tachmazidis and George Baryannis and Grigoris Antoniou",

year = "2020",

month = nov,

day = "11",

doi = "10.1007/978-3-030-62327-2\_7",

language = "English",

isbn = "9783030623265",

volume = "LNCS 12124",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "39--44",

editor = "Andreas Harth and Valentina Presutti and Rapha{\"e}l Troncy and Maribel Acosta and Axel Polleres and Fern{\'a}ndez, \{Javier D.\} and Parreira, \{Josiane Xavier\} and Olaf Hartig and Katja Hose and Michael Cochez",

booktitle = "The Semantic Web",

address = "Switzerland",

note = "Extended Semantic Web Conference 2020, ESWC2020 ; Conference date: 31-05-2020 Through 04-06-2020",

url = "https://2020.eswc-conferences.org/",

}

Batsakis, S, Tachmazidis, I , Baryannis, G & Antoniou, G 2020, Semantic Artificial Neural Networks. in A Harth, V Presutti, R Troncy, M Acosta, A Polleres, JD Fernández, JX Parreira, O Hartig, K Hose & M Cochez (eds), The Semantic Web: ESWC 2020 Satellite Events. vol. LNCS 12124, Lecture Notes in Computer Science, vol. LNCS 12124, Springer, Cham, Cham, pp. 39-44, Extended Semantic Web Conference 2020, Crete, Greece, 31/05/20. https://doi.org/10.1007/978-3-030-62327-2_7

Semantic Artificial Neural Networks. / Batsakis, Sotirios; Tachmazidis, Ilias ; Baryannis, George et al.
The Semantic Web: ESWC 2020 Satellite Events. ed. / Andreas Harth; Valentina Presutti; Raphaël Troncy; Maribel Acosta; Axel Polleres; Javier D. Fernández; Josiane Xavier Parreira; Olaf Hartig; Katja Hose; Michael Cochez. Vol. LNCS 12124 Cham: Springer, Cham, 2020. p. 39-44 (Lecture Notes in Computer Science; Vol. LNCS 12124).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Semantic Artificial Neural Networks

AU - Batsakis, Sotirios

AU - Tachmazidis, Ilias

AU - Baryannis, George

AU - Antoniou, Grigoris

PY - 2020/11/11

Y1 - 2020/11/11

N2 - 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.

AB - 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.

KW - Semantic Neural Networks

KW - Neural Networks

KW - Artificial intelligence (AI)

KW - Machine learning methods

UR - https://www.springer.com/gp/book/9783030623265

UR - https://www.scopus.com/pages/publications/85097291199

U2 - 10.1007/978-3-030-62327-2_7

DO - 10.1007/978-3-030-62327-2_7

M3 - Conference contribution

SN - 9783030623265

VL - LNCS 12124

T3 - Lecture Notes in Computer Science

SP - 39

EP - 44

BT - The Semantic Web

A2 - Harth, Andreas

A2 - Presutti, Valentina

A2 - Troncy, Raphaël

A2 - Acosta, Maribel

A2 - Polleres, Axel

A2 - Fernández, Javier D.

A2 - Parreira, Josiane Xavier

A2 - Hartig, Olaf

A2 - Hose, Katja

A2 - Cochez, Michael

PB - Springer, Cham

CY - Cham

T2 - Extended Semantic Web Conference 2020

Y2 - 31 May 2020 through 4 June 2020

ER -

Batsakis S, Tachmazidis I , Baryannis G, Antoniou G. Semantic Artificial Neural Networks. In Harth A, Presutti V, Troncy R, Acosta M, Polleres A, Fernández JD, Parreira JX, Hartig O, Hose K, Cochez M, editors, The Semantic Web: ESWC 2020 Satellite Events. Vol. LNCS 12124. Cham: Springer, Cham. 2020. p. 39-44. (Lecture Notes in Computer Science). Epub 2020 Nov 11. doi: 10.1007/978-3-030-62327-2_7

Semantic Artificial Neural Networks

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this