A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality
Artificial Intelligence
2023-09-20 v3 Logic in Computer Science
Neural and Evolutionary Computing
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.
Cite
@article{arxiv.2305.00304,
title = {A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality},
author = {Mario Alviano and Francesco Bartoli and Marco Botta and Roberto Esposito and Laura Giordano and Daniele Theseider Dupré},
journal= {arXiv preprint arXiv:2305.00304},
year = {2023}
}
Comments
arXiv admin note: text overlap with arXiv:2106.00390