Debated backpropagation

Isaac James; Christopher Luciano Stone; Alice Toniolo

Debated backpropagation

Isaac James^*, Christopher Luciano Stone^*, Alice Toniolo^*

^*Corresponding author for this work

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

19 Downloads (Pure)

Abstract

Dialogue has long been used in human society to explain seemingly opaque concepts. In this paper we focus on how to better explain training models for neural networks, to entertain as well as inform. We present a multi-agent argumentation-based dialogue system to generate human understandable dialogue to explain backpropagation. The system incorporates a model of agent personality and introduces social elements between agents to produce characterful discussion. Natural language templates are used to render utterances in English.

Original language	English
Title of host publication	Artificial Intelligence and Cognitive Science 2021
Subtitle of host publication	The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021
Editors	Arjun Pakrashi, Ellen Rushe, Mehran Hossein Zadeh Bazargani, Brian Mac Namee
Pages	260-271
Number of pages	12
Publication status	Published - 11 Mar 2022
Event	29th Irish Conference on Artificial Intelligence and Cognitive Science - University College Dublin, Dublin, Ireland Duration: 9 Dec 2019 → 10 Dec 2021 Conference number: 29 https://aics2021.ucd.ie

Publication series

Name	CEUR Workshop Proceedings
ISSN (Electronic)	1613-0073

Conference

Conference	29th Irish Conference on Artificial Intelligence and Cognitive Science
Abbreviated title	AICS21
Country/Territory	Ireland
City	Dublin
Period	9/12/19 → 10/12/21
Internet address	https://aics2021.ucd.ie

Keywords

Backpropogation
Explanation
Argumentation
Dialogue
NLG

Access to Document

James_2022_Debated-backpropogation_CC
Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Final published version, 385 KBLicence: CC BY

http://ceur-ws.org/Vol-3105/Licence: CC BY

Cite this

James, I., Stone, C. L., & Toniolo, A. (2022). Debated backpropagation. In A. Pakrashi, E. Rushe, M. H. Z. Bazargani, & B. Mac Namee (Eds.), Artificial Intelligence and Cognitive Science 2021: The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021 (pp. 260-271). (CEUR Workshop Proceedings). http://ceur-ws.org/Vol-3105/

James, Isaac ; Stone, Christopher Luciano ; Toniolo, Alice. / Debated backpropagation. Artificial Intelligence and Cognitive Science 2021: The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021. editor / Arjun Pakrashi ; Ellen Rushe ; Mehran Hossein Zadeh Bazargani ; Brian Mac Namee. 2022. pp. 260-271 (CEUR Workshop Proceedings).

@inproceedings{59c416f957f04a36a50201fb85a31563,

title = "Debated backpropagation",

abstract = "Dialogue has long been used in human society to explain seemingly opaque concepts. In this paper we focus on how to better explain training models for neural networks, to entertain as well as inform. We present a multi-agent argumentation-based dialogue system to generate human understandable dialogue to explain backpropagation. The system incorporates a model of agent personality and introduces social elements between agents to produce characterful discussion. Natural language templates are used to render utterances in English.",

keywords = "Backpropogation, Explanation, Argumentation, Dialogue, NLG",

author = "Isaac James and Stone, {Christopher Luciano} and Alice Toniolo",

year = "2022",

month = mar,

day = "11",

language = "English",

series = "CEUR Workshop Proceedings",

pages = "260--271",

editor = "Arjun Pakrashi and Ellen Rushe and Bazargani, {Mehran Hossein Zadeh} and {Mac Namee}, Brian",

booktitle = "Artificial Intelligence and Cognitive Science 2021",

note = "29th Irish Conference on Artificial Intelligence and Cognitive Science , AICS21 ; Conference date: 09-12-2019 Through 10-12-2021",

url = "https://aics2021.ucd.ie",

}

James, I, Stone, CL & Toniolo, A 2022, Debated backpropagation. in A Pakrashi, E Rushe, MHZ Bazargani & B Mac Namee (eds), Artificial Intelligence and Cognitive Science 2021: The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021. CEUR Workshop Proceedings, pp. 260-271, 29th Irish Conference on Artificial Intelligence and Cognitive Science , Dublin, Ireland, 9/12/19. <http://ceur-ws.org/Vol-3105/>

Debated backpropagation. / James, Isaac; Stone, Christopher Luciano ; Toniolo, Alice.
Artificial Intelligence and Cognitive Science 2021: The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021. ed. / Arjun Pakrashi; Ellen Rushe; Mehran Hossein Zadeh Bazargani; Brian Mac Namee. 2022. p. 260-271 (CEUR Workshop Proceedings).

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

TY - GEN

T1 - Debated backpropagation

AU - James, Isaac

AU - Stone, Christopher Luciano

AU - Toniolo, Alice

N1 - Conference code: 29

PY - 2022/3/11

Y1 - 2022/3/11

N2 - Dialogue has long been used in human society to explain seemingly opaque concepts. In this paper we focus on how to better explain training models for neural networks, to entertain as well as inform. We present a multi-agent argumentation-based dialogue system to generate human understandable dialogue to explain backpropagation. The system incorporates a model of agent personality and introduces social elements between agents to produce characterful discussion. Natural language templates are used to render utterances in English.

AB - Dialogue has long been used in human society to explain seemingly opaque concepts. In this paper we focus on how to better explain training models for neural networks, to entertain as well as inform. We present a multi-agent argumentation-based dialogue system to generate human understandable dialogue to explain backpropagation. The system incorporates a model of agent personality and introduces social elements between agents to produce characterful discussion. Natural language templates are used to render utterances in English.

KW - Backpropogation

KW - Explanation

KW - Argumentation

KW - Dialogue

KW - NLG

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

SP - 260

EP - 271

BT - Artificial Intelligence and Cognitive Science 2021

A2 - Pakrashi, Arjun

A2 - Rushe, Ellen

A2 - Bazargani, Mehran Hossein Zadeh

A2 - Mac Namee, Brian

T2 - 29th Irish Conference on Artificial Intelligence and Cognitive Science

Y2 - 9 December 2019 through 10 December 2021

ER -

Debated backpropagation

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this