Knowledge injection via ML-based initialization of neural networks


Hoffmann, Lars ; Bartelt, Christian ; Stuckenschmidt, Heiner


[img] PDF
short20.pdf - Published

Download (909kB)

Additional URL: http://ceur-ws.org/Vol-3052/
URN: urn:nbn:de:0074-3052-0
Document Type: Conference or workshop publication
Year of publication: 2021
Book title: Proceedings of the CIKM 2021 Workshops (CIKMW 2021) co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) : Gold Coast, Queensland, Australia, November 1-5,2021
The title of a journal, publication series: CEUR Workshop Proceedings
Volume: 3052
Page range: 1-6
Conference title: KINN 2021, 1st Workshop on Knowledge Injection in Neural Networks (KINN)
Location of the conference venue: Online
Date of the conference: 01.11.2021
Publisher: Cong, Gao ; Ramanath, Maya
Place of publication: Aachen, Germany
Publishing house: RWTH Aachen
ISSN: 1613-0073
Publication language: English
Institution: Außerfakultäre Einrichtungen > Institut für Enterprise Systems (InES)
School of Business Informatics and Mathematics > Praktische Informatik II (Stuckenschmidt 2009-)
Pre-existing license: Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
Keywords (English): knowledge injection , neural networks , initialization , machine learning
Abstract: Despite the success of artificial neural networks (ANNs) for various complex tasks, their performance and training duration heavily rely on several factors. In many application domains these requirements, such as high data volume and quality, are not satisfied. To tackle this issue, different ways to inject existing domain knowledge into the ANN generation provided promising results. However, the initialization of ANNs is mostly overlooked in this paradigm and remains an important scientific challenge. In this paper, we present a machine learning framework enabling an ANN to perform a semantic mapping from a well-defined, symbolic representation of domain knowledge to weights and biases of an ANN in a specified architecture.
Additional information: KINN 2021, 1st Workshop on Knowledge Injection in Neural Networks (KINN) fand am 1.11.2011 im Rahmen der CIKM 2021 statt -- Online-Ressource

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




Metadata export


Citation


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item