A framework for explainable deep neural models using external knowledge graphs

Zachary A. Daniels; Logan D. Frank; Christopher J. Menart; Michael Raymer; Pascal Hitzler

doi:10.1117/12.2558083

A framework for explainable deep neural models using external knowledge graphs

Zachary A. Daniels, Logan D. Frank, Christopher J. Menart, Michael Raymer, Pascal Hitzler

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

Original language	English
Title of host publication	Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II
Editors	Tien Pham, Latasha Solomon, Katie Rainey
Publisher	SPIE
ISBN (Electronic)	9781510636033
DOIs	https://doi.org/10.1117/12.2558083
State	Published - 2020
Externally published	Yes
Event	Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II 2020 - Virtual, Online, United States Duration: Apr 27 2020 → May 8 2020

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	11413
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II 2020
Country/Territory	United States
City	Virtual, Online
Period	4/27/20 → 5/8/20

ASJC Scopus Subject Areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Keywords

Deep Learning
Explainability
External Knowledge
Generalizability
Knowledge Graphs
Neural Networks
Scene Classification

Access to Document

10.1117/12.2558083

Cite this

Daniels, Z. A., Frank, L. D., Menart, C. J., Raymer, M., & Hitzler, P. (2020). A framework for explainable deep neural models using external knowledge graphs. In T. Pham, L. Solomon, & K. Rainey (Eds.), Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II Article 114131C (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11413). SPIE. https://doi.org/10.1117/12.2558083

A framework for explainable deep neural models using external knowledge graphs. / Daniels, Zachary A.; Frank, Logan D.; Menart, Christopher J. et al.
Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II. ed. / Tien Pham; Latasha Solomon; Katie Rainey. SPIE, 2020. 114131C (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11413).

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

Daniels, ZA, Frank, LD, Menart, CJ, Raymer, M & Hitzler, P 2020, A framework for explainable deep neural models using external knowledge graphs. in T Pham, L Solomon & K Rainey (eds), Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II., 114131C, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11413, SPIE, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II 2020, Virtual, Online, United States, 4/27/20. https://doi.org/10.1117/12.2558083

Daniels ZA, Frank LD, Menart CJ, Raymer M, Hitzler P. A framework for explainable deep neural models using external knowledge graphs. In Pham T, Solomon L, Rainey K, editors, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II. SPIE. 2020. 114131C. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2558083

Daniels, Zachary A. ; Frank, Logan D. ; Menart, Christopher J. et al. / A framework for explainable deep neural models using external knowledge graphs. Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II. editor / Tien Pham ; Latasha Solomon ; Katie Rainey. SPIE, 2020. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{401624f1054f49f09a08768a022967eb,

title = "A framework for explainable deep neural models using external knowledge graphs",

keywords = "Deep Learning, Explainability, External Knowledge, Generalizability, Knowledge Graphs, Neural Networks, Scene Classification",

author = "Daniels, {Zachary A.} and Frank, {Logan D.} and Menart, {Christopher J.} and Michael Raymer and Pascal Hitzler",

note = "Publisher Copyright: {\textcopyright} 2020 SPIE.; Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II 2020 ; Conference date: 27-04-2020 Through 08-05-2020",

year = "2020",

doi = "10.1117/12.2558083",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Tien Pham and Latasha Solomon and Katie Rainey",

booktitle = "Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II",

}

TY - GEN

T1 - A framework for explainable deep neural models using external knowledge graphs

AU - Daniels, Zachary A.

AU - Frank, Logan D.

AU - Menart, Christopher J.

AU - Raymer, Michael

AU - Hitzler, Pascal

PY - 2020

Y1 - 2020

KW - Deep Learning

KW - Explainability

KW - External Knowledge

KW - Generalizability

KW - Knowledge Graphs

KW - Neural Networks

KW - Scene Classification

UR - http://www.scopus.com/inward/record.url?scp=85089182419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089182419&partnerID=8YFLogxK

U2 - 10.1117/12.2558083

DO - 10.1117/12.2558083

M3 - Conference contribution

AN - SCOPUS:85089182419

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II

A2 - Pham, Tien

A2 - Solomon, Latasha

A2 - Rainey, Katie

PB - SPIE

T2 - Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II 2020

Y2 - 27 April 2020 through 8 May 2020

ER -

A framework for explainable deep neural models using external knowledge graphs

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Cite this