Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension

This paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective. This is an early exploration paper aiming to understand whether paraconsistent analysis can be applied for understanding neural networks and whether it is worth further develop th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Francisco S. Marcondes, Dalila Durães, Flávio Santos, José João Almeida, Paulo Novais
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	paraconsistent logic explainable AI neural network Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/379b49d3b1c84723b28939aaae538024
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:379b49d3b1c84723b28939aaae538024
record_format	dspace
spelling	oai:doaj.org-article:379b49d3b1c84723b28939aaae5380242021-11-11T15:39:32ZNeural Network Explainable AI Based on Paraconsistent Analysis: An Extension10.3390/electronics102126602079-9292https://doaj.org/article/379b49d3b1c84723b28939aaae5380242021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2660https://doaj.org/toc/2079-9292This paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective. This is an early exploration paper aiming to understand whether paraconsistent analysis can be applied for understanding neural networks and whether it is worth further develop the subject in future research. The answers to these two questions are affirmative. Paraconsistent analysis provides insightful prediction visualisation through a mature formal framework that provides proper support for reasoning. The significant potential envisioned is the that paraconsistent analysis will be used for guiding neural network development projects, despite the performance issues. This paper provides two explorations. The first was a baseline experiment based on MNIST for establishing the link between paraconsistency and neural networks. The second experiment aimed to detect violence in audio files to verify whether the paraconsistent framework scales to industry level problems. The conclusion shown by this early assessment is that further research on this subject is worthful, and may eventually result in a significant contribution to the field.Francisco S. MarcondesDalila DurãesFlávio SantosJosé João AlmeidaPaulo NovaisMDPI AGarticleparaconsistent logicexplainable AIneural networkElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2660, p 2660 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	paraconsistent logic explainable AI neural network Electronics TK7800-8360
spellingShingle	paraconsistent logic explainable AI neural network Electronics TK7800-8360 Francisco S. Marcondes Dalila Durães Flávio Santos José João Almeida Paulo Novais Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
description	This paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective. This is an early exploration paper aiming to understand whether paraconsistent analysis can be applied for understanding neural networks and whether it is worth further develop the subject in future research. The answers to these two questions are affirmative. Paraconsistent analysis provides insightful prediction visualisation through a mature formal framework that provides proper support for reasoning. The significant potential envisioned is the that paraconsistent analysis will be used for guiding neural network development projects, despite the performance issues. This paper provides two explorations. The first was a baseline experiment based on MNIST for establishing the link between paraconsistency and neural networks. The second experiment aimed to detect violence in audio files to verify whether the paraconsistent framework scales to industry level problems. The conclusion shown by this early assessment is that further research on this subject is worthful, and may eventually result in a significant contribution to the field.
format	article
author	Francisco S. Marcondes Dalila Durães Flávio Santos José João Almeida Paulo Novais
author_facet	Francisco S. Marcondes Dalila Durães Flávio Santos José João Almeida Paulo Novais
author_sort	Francisco S. Marcondes
title	Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
title_short	Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
title_full	Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
title_fullStr	Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
title_full_unstemmed	Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension
title_sort	neural network explainable ai based on paraconsistent analysis: an extension
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/379b49d3b1c84723b28939aaae538024
work_keys_str_mv	AT franciscosmarcondes neuralnetworkexplainableaibasedonparaconsistentanalysisanextension AT daliladuraes neuralnetworkexplainableaibasedonparaconsistentanalysisanextension AT flaviosantos neuralnetworkexplainableaibasedonparaconsistentanalysisanextension AT josejoaoalmeida neuralnetworkexplainableaibasedonparaconsistentanalysisanextension AT paulonovais neuralnetworkexplainableaibasedonparaconsistentanalysisanextension
_version_	1718434592831045632

Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension

Ejemplares similares