Bearbeite Veranstaltung: Modeling Concept Learning Problems with Second-Order Description Logics

Du bist aus dem folgenden Grund nicht berechtigt, diese Seite bearbeiten:

Diese Aktion ist auf Benutzer beschränkt, die der Gruppe „Benutzer“ angehören.

Event

Title DE:

German title

Title EN:

English title; when creating new events, this will be used to define the page name (which will not change even if you change it later)

Description DE:

Abstract or other additional information in German

Description EN:
Among the inferences studied in Description Logics (DLs), induction has been paid increasing attention over the last decade. Indeed, useful non-standard reasoning tasks can be based on the inductive inference. Among them, Concept Learning is about the automated induction of a description for a given concept starting from classified instances of the concept. In this talk I present a formal characterization of Concept Learning in DLs which relies on recent results in Knowledge Representation and Machine Learning. Based on second-order DLs, it allows for modeling Concept Learning problems as constructive DL reasoning tasks where the construction of the solution to the problem may be subject to optimality criteria.

Abstract or other additional information in English

Type of event:

Explanation of possible values

Start:
::

Start of event (date and time); required field

End:
::

End of event (date and time)

Location:

Room where the event is happening

Speaker:

Person who is presenting or chairing; usually the full name without titles

Invited by:

For presentations by a guest speaker, the person who invited her/him

PDF:
Datei hochladen

Optional file download

URL:

Optional URL for the event

Research group:

Related research group (use Ctrl+click for marking/unmarking multiple entries)

Event series:

Related event series (use Ctrl+click for marking/unmarking multiple entries); leave empty if not related to any series

Show on main page:

Events only appear on the main page if this is set to 1

Zusammenfassung:

Abbrechen