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.
A multipreference semantics from common sense reasoning to neural network models: An overview
Giordano L.;Theseider Dupre' Daniele.
2021-01-01
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.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
