In this section
@unpublished{Albini:2021,
author = {Albini, E and Lertvittayakumjorn, P and Rago, A and Toni, F},
publisher = {arXiv},
title = {DAX: deep argumentative eXplanation for neural networks},
url = {http://arxiv.org/abs/2012.05766v2},
year = {2021}
}
TY - UNPB
AB - Despite the rapid growth in attention on eXplainable AI (XAI) of late,explanations in the literature provide little insight into the actualfunctioning of Neural Networks (NNs), significantly limiting theirtransparency. We propose a methodology for explaining NNs, providingtransparency about their inner workings, by utilising computationalargumentation (a form of symbolic AI offering reasoning abstractions for avariety of settings where opinions matter) as the scaffolding underpinning DeepArgumentative eXplanations (DAXs). We define three DAX instantiations (forvarious neural architectures and tasks) and evaluate them empirically in termsof stability, computational cost, and importance of depth. We also conducthuman experiments with DAXs for text classification models, indicating thatthey are comprehensible to humans and align with their judgement, while alsobeing competitive, in terms of user acceptance, with existing approaches to XAIthat also have an argumentative spirit.
AU - Albini,E
AU - Lertvittayakumjorn,P
AU - Rago,A
AU - Toni,F
PB - arXiv
PY - 2021///
TI - DAX: deep argumentative eXplanation for neural networks
UR - http://arxiv.org/abs/2012.05766v2
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: