In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a multilayer neural network model. Weighted knowledge bases for a simple description logic with typicality are considered under a (many-valued) “concept-wise” multipreference semantics. The semantics is used to provide a preferential interpretation of MultiLayer Perceptrons (MLPs). A model checking and an entailment based approach are exploited in the verification of conditional properties of MLPs.
A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality
Botta, Marco;Esposito, Roberto;
In corso di stampa
Abstract
In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a multilayer neural network model. Weighted knowledge bases for a simple description logic with typicality are considered under a (many-valued) “concept-wise” multipreference semantics. The semantics is used to provide a preferential interpretation of MultiLayer Perceptrons (MLPs). A model checking and an entailment based approach are exploited in the verification of conditional properties of MLPs.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
A preferential interpretation.pdf
Accesso aperto
Tipo di file:
PDF EDITORIALE
Dimensione
969.55 kB
Formato
Adobe PDF
|
969.55 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
