Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model
| Autor: | Laura Giordano, Daniele Theseider Dupré |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Interpretation (logic)
Knowledge representation and reasoning Artificial neural network Computer science business.industry Semantics (computer science) Computer Science::Neural and Evolutionary Computation Defeasible estate Fuzzy logic Description logic Computer Science::Logic in Computer Science Defeasible reasoning Artificial intelligence business |
| Zdroj: | Logics in Artificial Intelligence ISBN: 9783030757748 JELIA |
| Popis: | In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a deep neural network model. Weighted knowledge bases for description logics are considered under a “concept-wise” multipreference semantics. The semantics is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons, under some condition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|