Explaining trained neural networks with Semantic Web Technologies: First steps

Md Kamruzzaman Sarker; Ning Xie; Derek Doran; Michael Raymer; Pascal Hitzler

Explaining trained neural networks with Semantic Web Technologies: First steps

Md Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael Raymer, Pascal Hitzler

Research output: Contribution to journal › Conference article › peer-review

Abstract

The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	2003
State	Published - 2017
Event	12th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2017 - London, United Kingdom Duration: Jul 17 2017 → Jul 18 2017

ASJC Scopus Subject Areas

General Computer Science

Keywords

Neural networks
Conceptual apporaches
Input-output behavior
New applications
Proof of concept
Semantic Web Technology
Structured data
Trained neural networks
Semantic Web

Disciplines

Computer Sciences

Access to Document

Explaining Trained Neural Networks with Semantic Web TechnologiesFinal published version, 2.17 MB

Cite this

@article{8c74262690b243838849310af8a677b8,

title = "Explaining trained neural networks with Semantic Web Technologies: First steps",

abstract = "The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.",

keywords = "Neural networks, Conceptual apporaches, Input-output behavior, New applications, Proof of concept, Semantic Web Technology, Structured data, Trained neural networks, Semantic Web",

author = "Sarker, {Md Kamruzzaman} and Ning Xie and Derek Doran and Michael Raymer and Pascal Hitzler",

note = "Publisher Copyright: Copyright {\textcopyright} 2017 for this paper by its authors.; 12th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2017 ; Conference date: 17-07-2017 Through 18-07-2017",

year = "2017",

language = "English",

volume = "2003",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

}

TY - JOUR

T1 - Explaining trained neural networks with Semantic Web Technologies

T2 - 12th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2017

AU - Sarker, Md Kamruzzaman

AU - Xie, Ning

AU - Doran, Derek

AU - Raymer, Michael

AU - Hitzler, Pascal

PY - 2017

Y1 - 2017

N2 - The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.

AB - The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.

KW - Neural networks

KW - Conceptual apporaches

KW - Input-output behavior

KW - New applications

KW - Proof of concept

KW - Semantic Web Technology

KW - Structured data

KW - Trained neural networks

KW - Semantic Web

UR - http://www.scopus.com/inward/record.url?scp=85037100768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037100768&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85037100768

SN - 1613-0073

VL - 2003

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 17 July 2017 through 18 July 2017

ER -

Explaining trained neural networks with Semantic Web Technologies: First steps

Abstract

ASJC Scopus Subject Areas

Keywords

Disciplines

Access to Document

Other files and links

Cite this