Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model

Laura GIORDANO; Daniele THESEIDER DUPRE'

doi:10.1007/978-3-030-75775-5_16

Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model

Department of Science and Technological Innovation

Research output: Contribution to conference › Paper › peer-review

Abstract

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.

Original language	English
Pages	225-242
Number of pages	18
DOIs	https://doi.org/10.1007/978-3-030-75775-5_16
Publication status	Published - 1 Jan 2021
Event	17th European Conference on Logics in Artiﬁcial Intelligence, JELIA 2021 - Virtual Event Duration: 1 Jan 2021 → …

Conference

Conference	17th European Conference on Logics in Artiﬁcial Intelligence, JELIA 2021
City	Virtual Event
Period	1/01/21 → …

Access to Document

10.1007/978-3-030-75775-5_16

http://hdl.handle.net/11579/131792

Cite this

@conference{7d8f3001473d4c32b3afd9b7c3e324bf,

title = "Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model",

abstract = "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 {\textquotedblleft}concept-wise{\textquotedblright} multipreference semantics. The semantics is further extended to fuzzy interpretations and exploited to provide a preferential interpretation of Multilayer Perceptrons, under some condition.",

author = "Laura GIORDANO and \{THESEIDER DUPRE'\}, Daniele",

year = "2021",

month = jan,

day = "1",

doi = "10.1007/978-3-030-75775-5\_16",

language = "English",

pages = "225--242",

note = "17th European Conference on Logics in Artiﬁcial Intelligence, JELIA 2021 ; Conference date: 01-01-2021",

}

TY - CONF

T1 - Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model

AU - GIORDANO, Laura

AU - THESEIDER DUPRE', Daniele

PY - 2021/1/1

Y1 - 2021/1/1

N2 - 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.

AB - 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.

UR - https://iris.uniupo.it/handle/11579/131792

U2 - 10.1007/978-3-030-75775-5_16

DO - 10.1007/978-3-030-75775-5_16

M3 - Paper

SP - 225

EP - 242

T2 - 17th European Conference on Logics in Artiﬁcial Intelligence, JELIA 2021

Y2 - 1 January 2021

ER -

Weighted Defeasible Knowledge Bases and a Multipreference Semantics for a Deep Neural Network Model

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this