This short paper reports on a line of research exploiting a conditional logic of commonsense reasoning to provide a semantic interpretation to neural network models. A “concept-wise" multi-preferential semantics for conditionals is exploited to build a preferential interpretation of a trained neural network starting from its input-output behavior. The approach is a general one; it has first been proposed for Self-Organising Maps (SOMs), and exploited for MultiLayer Perceptrons (MLPs) in the verification of properties of a network by model-checking. An MLPs can be regarded as a (fuzzy) conditional knowledge base (KB), in which the synaptic connections correspond to weighted conditionals. Reasoners for many- valued weighted conditional KBs are under development based on Answer Set solving to deal with entailment and model-checking.

Towards a Conditional and Multi-preferential Approach to Explainability of Neural Network Models in Computational Logic (Extended Abstract)

Botta M.;Esposito R.;Gliozzi V.;
2022-01-01

Abstract

This short paper reports on a line of research exploiting a conditional logic of commonsense reasoning to provide a semantic interpretation to neural network models. A “concept-wise" multi-preferential semantics for conditionals is exploited to build a preferential interpretation of a trained neural network starting from its input-output behavior. The approach is a general one; it has first been proposed for Self-Organising Maps (SOMs), and exploited for MultiLayer Perceptrons (MLPs) in the verification of properties of a network by model-checking. An MLPs can be regarded as a (fuzzy) conditional knowledge base (KB), in which the synaptic connections correspond to weighted conditionals. Reasoners for many- valued weighted conditional KBs are under development based on Answer Set solving to deal with entailment and model-checking.
2022
Inglese
contributo
4 - Workshop
3rd Italian Workshop on Explainable Artificiale Intelligence | co-located with AI*IA 2022
Udine
28/12/2022
Internazionale
Cataldo Musto, Riccardo Guidotti, Anna Monreale, Giovanni Semeraro
Proceedings of the 3rd Italian Workshop on Explainable Artificial Intelligence co-located with 21th International Conference of the Italian Association for Artificial Intelligence(AIxIA 2022)
Comitato scientifico
CEUR
Aachen
GERMANIA
3277
64
72
9
https://ceur-ws.org/Vol-3277/short1.pdf
Preferential Description Logics, Typicality, Neural Networks, Explainability
no
1 – prodotto con file in versione Open Access (allegherò il file al passo 6 - Carica)
7
info:eu-repo/semantics/conferenceObject
04-CONTRIBUTO IN ATTI DI CONVEGNO::04A-Conference paper in volume
Alviano M.; Bartoli F.; Botta M.; Esposito R.; Giordano L.; Gliozzi V.; Dupre D.T.
273
open
File in questo prodotto:
File Dimensione Formato  
short1.pdf

Accesso aperto

Descrizione: Main paper
Tipo di file: PDF EDITORIALE
Dimensione 926.12 kB
Formato Adobe PDF
926.12 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1892056
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact