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.
Citation
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 . 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/ > conference
Publication
Artificial Intelligence and Cognitive Science 2021
ISSN
1613-0073Type
Conference item
Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.