Multilayer Perceptrons as Weighted Conditional Knowledge Bases: An Overview

Laura Giordano; Daniele Theseider Dupré

Multilayer Perceptrons as Weighted Conditional Knowledge Bases: An Overview

Department of Science and Technological Innovation

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we report about the relationships between a multi-preferential semantics for defeasible description logics and a deep neural network model. Weighted knowledge bases for description logics are considered under a “concept-wise" preferential semantics, which is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.

Original language	English
Pages (from-to)	10-18
Number of pages	9
Journal	CEUR Workshop Proceedings
Volume	3078
Publication status	Published - 2022
Event	2021 International Conference of the Italian Association for Artificial Intelligence, AIxIA 2021 DP - Virtual, Online Duration: 1 Dec 2021 → 3 Dec 2021

Keywords

Common sense reasoning
Neural networks
Preferential semantics
Weighted conditionals

Cite this

@article{c5bb3b5bf430436eaa36bb993bec5d95,

title = "Multilayer Perceptrons as Weighted Conditional Knowledge Bases: An Overview",

abstract = "In this paper we report about the relationships between a multi-preferential semantics for defeasible description logics and a deep neural network model. Weighted knowledge bases for description logics are considered under a “concept-wise{"} preferential semantics, which is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.",

keywords = "Common sense reasoning, Neural networks, Preferential semantics, Weighted conditionals",

author = "Laura Giordano and Dupr{\'e}, \{Daniele Theseider\}",

note = "Publisher Copyright: {\textcopyright} 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (CEUR-WS.org); 2021 International Conference of the Italian Association for Artificial Intelligence, AIxIA 2021 DP ; Conference date: 01-12-2021 Through 03-12-2021",

year = "2022",

language = "English",

volume = "3078",

pages = "10--18",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Multilayer Perceptrons as Weighted Conditional Knowledge Bases

T2 - 2021 International Conference of the Italian Association for Artificial Intelligence, AIxIA 2021 DP

AU - Giordano, Laura

AU - Dupré, Daniele Theseider

N1 - Publisher Copyright: © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (CEUR-WS.org)

PY - 2022

Y1 - 2022

N2 - In this paper we report about the relationships between a multi-preferential semantics for defeasible description logics and a deep neural network model. Weighted knowledge bases for description logics are considered under a “concept-wise" preferential semantics, which is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.

AB - In this paper we report about the relationships between a multi-preferential semantics for defeasible description logics and a deep neural network model. Weighted knowledge bases for description logics are considered under a “concept-wise" preferential semantics, which is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons.

KW - Common sense reasoning

KW - Neural networks

KW - Preferential semantics

KW - Weighted conditionals

UR - https://www.scopus.com/pages/publications/85124381679

M3 - Conference article

AN - SCOPUS:85124381679

SN - 1613-0073

VL - 3078

SP - 10

EP - 18

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 1 December 2021 through 3 December 2021

ER -

Multilayer Perceptrons as Weighted Conditional Knowledge Bases: An Overview

Abstract

Keywords

Other files and links

Fingerprint

Cite this