A multipreference semantics from common sense reasoning to neural network models: An overview

Risultato della ricerca: Contributo su rivistaArticolo da conferenzapeer review

Abstract

In this short paper we report about a "concept-wise" multipreference semantics for weighted conditionals and its use to provide a logical interpretation to some neural network models, Self-Organising Maps (SOMs) and Multilayer Perceptrons (MLPs). For MLPs, a deep network can be regarded as a conditional knowledge base, in which the synaptic connections correspond to weighted conditionals.

Lingua originaleInglese
RivistaCEUR Workshop Proceedings
Volume2969
Stato di pubblicazionePubblicato - 2021
EventoJoint Ontology Workshops 2021 Episode VII: The Bolzano Summer of Knowledge, JOWO 2021 - Bolzano, Italy
Durata: 11 set 202118 set 2021

Fingerprint

Entra nei temi di ricerca di 'A multipreference semantics from common sense reasoning to neural network models: An overview'. Insieme formano una fingerprint unica.

Cita questo