Machine Education: Designing semantically ordered and ontologically guided modular neural networks

Hussein Abbass; Sondoss  El-Sawah; Eleni Petraki; Robert Hunjet

doi:10.1109/SSCI44817.2019.9003083

Machine Education: Designing semantically ordered and ontologically guided modular neural networks

Hussein Abbass, Sondoss El-Sawah, Eleni Petraki, Robert Hunjet

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

14 Citations (Scopus)

Abstract

The literature on machine teaching, machine education, and curriculum design for machines is in its infancy with sparse papers on the topic primarily focusing on data and model engineering factors to improve machine learning. In this paper, we first discuss selected attempts to date on machine teaching and education. We then bring theories and methodologies together from human education to structure and mathematically define the core problems in lesson design for machine education and the modelling approaches required to support the steps for machine education. Last, but not least, we offer an ontology-based methodology to guide the development of lesson plans to produce transparent and explainable modular learning machines, including neural networks.

Original language	English
Title of host publication	Machine Education: Designing semantically ordered and ontologically guided modular neural networks
Editors	Zengguang Hou, Amir Hussain, Chunhua Yang, Zhigang Zeng, Yi Zhang
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	948-955
Number of pages	8
ISBN (Electronic)	9781728124858
ISBN (Print)	9781728124865
DOIs	https://doi.org/10.1109/SSCI44817.2019.9003083
Publication status	Published - Dec 2019
Event	SSCI 2019 IEEE Symposium Series on Computational Intelligence - Xiamen, Xiamen, China Duration: 6 Dec 2019 → 9 Dec 2019 http://ssci2019.org/

Publication series

Name	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Conference

Conference	SSCI 2019 IEEE Symposium Series on Computational Intelligence
Abbreviated title	SSCI 2019
Country/Territory	China
City	Xiamen
Period	6/12/19 → 9/12/19
Internet address	http://ssci2019.org/

Access to Document

10.1109/SSCI44817.2019.9003083

https://arxiv.org/pdf/2002.03841.pdf

Cite this

Abbass, H., El-Sawah, S., Petraki, E., & Hunjet, R. (2019). Machine Education: Designing semantically ordered and ontologically guided modular neural networks. In Z. Hou, A. Hussain, C. Yang, Z. Zeng, & Y. Zhang (Eds.), Machine Education: Designing semantically ordered and ontologically guided modular neural networks (pp. 948-955). Article 9003083 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SSCI44817.2019.9003083

Abbass, Hussein ; El-Sawah, Sondoss ; Petraki, Eleni et al. / Machine Education: Designing semantically ordered and ontologically guided modular neural networks. Machine Education: Designing semantically ordered and ontologically guided modular neural networks . editor / Zengguang Hou ; Amir Hussain ; Chunhua Yang ; Zhigang Zeng ; Yi Zhang. United States : IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 948-955 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

@inproceedings{56ea046bbb9e489cb28958d066856b78,

title = "Machine Education: Designing semantically ordered and ontologically guided modular neural networks",

abstract = "The literature on machine teaching, machine education, and curriculum design for machines is in its infancy with sparse papers on the topic primarily focusing on data and model engineering factors to improve machine learning. In this paper, we first discuss selected attempts to date on machine teaching and education. We then bring theories and methodologies together from human education to structure and mathematically define the core problems in lesson design for machine education and the modelling approaches required to support the steps for machine education. Last, but not least, we offer an ontology-based methodology to guide the development of lesson plans to produce transparent and explainable modular learning machines, including neural networks.",

keywords = "curriculum design, machine education, machine teaching, transparent and explainable modular neural networks.",

author = "Hussein Abbass and Sondoss El-Sawah and Eleni Petraki and Robert Hunjet",

note = "Funding Information: The authors would like to acknowledge the US Office of Naval Research - Global (ONR-G) Grant and the Air Force Office of Scientific Research under award number FA2386-17-1-4054. Publisher Copyright: {\textcopyright} 2019 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; SSCI 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 ; Conference date: 06-12-2019 Through 09-12-2019",

year = "2019",

month = dec,

doi = "10.1109/SSCI44817.2019.9003083",

language = "English",

isbn = "9781728124865",

series = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "948--955",

editor = "Zengguang Hou and Amir Hussain and Chunhua Yang and Zhigang Zeng and Yi Zhang",

booktitle = "Machine Education: Designing semantically ordered and ontologically guided modular neural networks",

address = "United States",

url = "http://ssci2019.org/",

}

Abbass, H, El-Sawah, S, Petraki, E & Hunjet, R 2019, Machine Education: Designing semantically ordered and ontologically guided modular neural networks. in Z Hou, A Hussain, C Yang, Z Zeng & Y Zhang (eds), Machine Education: Designing semantically ordered and ontologically guided modular neural networks ., 9003083, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 948-955, SSCI 2019 IEEE Symposium Series on Computational Intelligence, Xiamen, China, 6/12/19. https://doi.org/10.1109/SSCI44817.2019.9003083

Machine Education: Designing semantically ordered and ontologically guided modular neural networks. / Abbass, Hussein; El-Sawah, Sondoss ; Petraki, Eleni et al.
Machine Education: Designing semantically ordered and ontologically guided modular neural networks . ed. / Zengguang Hou; Amir Hussain; Chunhua Yang; Zhigang Zeng; Yi Zhang. United States: IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 948-955 9003083 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Machine Education: Designing semantically ordered and ontologically guided modular neural networks

AU - Abbass, Hussein

AU - El-Sawah, Sondoss

AU - Petraki, Eleni

AU - Hunjet, Robert

N1 - Funding Information: The authors would like to acknowledge the US Office of Naval Research - Global (ONR-G) Grant and the Air Force Office of Scientific Research under award number FA2386-17-1-4054. Publisher Copyright: © 2019 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2019/12

Y1 - 2019/12

N2 - The literature on machine teaching, machine education, and curriculum design for machines is in its infancy with sparse papers on the topic primarily focusing on data and model engineering factors to improve machine learning. In this paper, we first discuss selected attempts to date on machine teaching and education. We then bring theories and methodologies together from human education to structure and mathematically define the core problems in lesson design for machine education and the modelling approaches required to support the steps for machine education. Last, but not least, we offer an ontology-based methodology to guide the development of lesson plans to produce transparent and explainable modular learning machines, including neural networks.

AB - The literature on machine teaching, machine education, and curriculum design for machines is in its infancy with sparse papers on the topic primarily focusing on data and model engineering factors to improve machine learning. In this paper, we first discuss selected attempts to date on machine teaching and education. We then bring theories and methodologies together from human education to structure and mathematically define the core problems in lesson design for machine education and the modelling approaches required to support the steps for machine education. Last, but not least, we offer an ontology-based methodology to guide the development of lesson plans to produce transparent and explainable modular learning machines, including neural networks.

KW - curriculum design

KW - machine education

KW - machine teaching

KW - transparent and explainable modular neural networks.

UR - http://www.scopus.com/inward/record.url?scp=85080908160&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/46338a8c-71e5-3a9d-9e54-0eb679df1f48/

U2 - 10.1109/SSCI44817.2019.9003083

DO - 10.1109/SSCI44817.2019.9003083

M3 - Conference contribution

SN - 9781728124865

T3 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

SP - 948

EP - 955

BT - Machine Education: Designing semantically ordered and ontologically guided modular neural networks

A2 - Hou, Zengguang

A2 - Hussain, Amir

A2 - Yang, Chunhua

A2 - Zeng, Zhigang

A2 - Zhang, Yi

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - SSCI 2019 IEEE Symposium Series on Computational Intelligence

Y2 - 6 December 2019 through 9 December 2019

ER -

Abbass H, El-Sawah S, Petraki E, Hunjet R. Machine Education: Designing semantically ordered and ontologically guided modular neural networks. In Hou Z, Hussain A, Yang C, Zeng Z, Zhang Y, editors, Machine Education: Designing semantically ordered and ontologically guided modular neural networks . United States: IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 948-955. 9003083. (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). doi: 10.1109/SSCI44817.2019.9003083

Machine Education: Designing semantically ordered and ontologically guided modular neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this