Interactive Learning of Grounded Concepts

Jens Nevens; Paul Van Eecke; Katrien Beuls

Samenvatting

In this interactive demo, we introduce a novel approach to grounded concept learning. Using the language game methodology, we set up a tutor-learner scenario where the learner is an autonomous agent, grounded in the world using a Nao humanoid robot, and the participant is its tutor. For each concept, the robot has to find out which data streams are important and what the typical values for each data stream within a concept are. To make these decisions, the learner makes use of the notion of discrimination, i.e. separating one particular object from the other objects in the scene. Over the course of many such interactions, the learner incrementally and in real-time builds a complete repertoire of concepts that is functional in the world. A video of the demonstration can be found at https://ehai.ai. vub.ac.be/demos/interactive-concept-learning.

Originele taal-2	English
Titel	Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)
Redacteuren	Katrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, Paul Van Eecke
Uitgeverij	CEUR Workshop Proceedings
Aantal pagina's	2
Volume	2491
ISBN van elektronische versie	1613-0073
Status	Published - 6 nov 2019
Evenement	BNAIC 2019 - Brussels, Belgium Duur: 7 nov 2019 → 8 nov 2019

Publicatie series

Naam	CEUR Workshop Proceedings
ISSN van geprinte versie	1613-0073

Conference

Conference	BNAIC 2019
Land/Regio	Belgium
Stad	Brussels
Periode	7/11/19 → 8/11/19

Toegang tot document

http://ceur-ws.org/Vol-2491/demo85.pdf

Andere bestanden en links

Link to publication in Scopus

FWOSB64: Hybride AI om natuurlijke taal om te zetten in uitvoerbare betekenissen
Nevens, J., Beuls, K. & Nowe, A.
1/01/19 → 31/12/22
Project: Fundamenteel

Citeer dit

Nevens, J., Van Eecke, P., & Beuls, K. (2019). Interactive Learning of Grounded Concepts. In K. Beuls, B. Bogaerts, G. Bontempi, P. Geurts, N. Harley, B. Lebichot, T. Lenaerts, G. Louppe, & P. Van Eecke (editors), Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) (Vol. 2491). (CEUR Workshop Proceedings). CEUR Workshop Proceedings. http://ceur-ws.org/Vol-2491/demo85.pdf

Nevens, Jens ; Van Eecke, Paul ; Beuls, Katrien. / Interactive Learning of Grounded Concepts. Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). redacteur / Katrien Beuls ; Bart Bogaerts ; Gianluca Bontempi ; Pierre Geurts ; Nick Harley ; Bertrand Lebichot ; Tom Lenaerts ; Gilles Louppe ; Paul Van Eecke. Vol. 2491 CEUR Workshop Proceedings, 2019. (CEUR Workshop Proceedings).

@inbook{4b195aae3e2a4e93a298feb9b89bd818,

title = "Interactive Learning of Grounded Concepts",

abstract = "In this interactive demo, we introduce a novel approach to grounded concept learning. Using the language game methodology, we set up a tutor-learner scenario where the learner is an autonomous agent, grounded in the world using a Nao humanoid robot, and the participant is its tutor. For each concept, the robot has to find out which data streams are important and what the typical values for each data stream within a concept are. To make these decisions, the learner makes use of the notion of discrimination, i.e. separating one particular object from the other objects in the scene. Over the course of many such interactions, the learner incrementally and in real-time builds a complete repertoire of concepts that is functional in the world. A video of the demonstration can be found at https://ehai.ai. vub.ac.be/demos/interactive-concept-learning.",

author = "Jens Nevens and {Van Eecke}, Paul and Katrien Beuls",

year = "2019",

month = nov,

day = "6",

language = "English",

volume = "2491",

series = "CEUR Workshop Proceedings",

publisher = "CEUR Workshop Proceedings",

editor = "Katrien Beuls and Bart Bogaerts and Gianluca Bontempi and Geurts, {Pierre } and Nick Harley and Bertrand Lebichot and Tom Lenaerts and Gilles Louppe and {Van Eecke}, Paul",

booktitle = "Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)",

note = "BNAIC 2019 ; Conference date: 07-11-2019 Through 08-11-2019",

}

Nevens, J, Van Eecke, P & Beuls, K 2019, Interactive Learning of Grounded Concepts. in K Beuls, B Bogaerts, G Bontempi, P Geurts, N Harley, B Lebichot, T Lenaerts, G Louppe & P Van Eecke (redactie), Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). vol. 2491, CEUR Workshop Proceedings, CEUR Workshop Proceedings, BNAIC 2019, Brussels, Belgium, 7/11/19. <http://ceur-ws.org/Vol-2491/demo85.pdf>

Interactive Learning of Grounded Concepts. / Nevens, Jens; Van Eecke, Paul; Beuls, Katrien.

Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). redactie / Katrien Beuls; Bart Bogaerts; Gianluca Bontempi; Pierre Geurts; Nick Harley; Bertrand Lebichot; Tom Lenaerts; Gilles Louppe; Paul Van Eecke. Vol. 2491 CEUR Workshop Proceedings, 2019. (CEUR Workshop Proceedings).

Onderzoeksoutput: Meeting abstract (Book) › Research

TY - CHAP

T1 - Interactive Learning of Grounded Concepts

AU - Nevens, Jens

AU - Van Eecke, Paul

AU - Beuls, Katrien

PY - 2019/11/6

Y1 - 2019/11/6

N2 - In this interactive demo, we introduce a novel approach to grounded concept learning. Using the language game methodology, we set up a tutor-learner scenario where the learner is an autonomous agent, grounded in the world using a Nao humanoid robot, and the participant is its tutor. For each concept, the robot has to find out which data streams are important and what the typical values for each data stream within a concept are. To make these decisions, the learner makes use of the notion of discrimination, i.e. separating one particular object from the other objects in the scene. Over the course of many such interactions, the learner incrementally and in real-time builds a complete repertoire of concepts that is functional in the world. A video of the demonstration can be found at https://ehai.ai. vub.ac.be/demos/interactive-concept-learning.

AB - In this interactive demo, we introduce a novel approach to grounded concept learning. Using the language game methodology, we set up a tutor-learner scenario where the learner is an autonomous agent, grounded in the world using a Nao humanoid robot, and the participant is its tutor. For each concept, the robot has to find out which data streams are important and what the typical values for each data stream within a concept are. To make these decisions, the learner makes use of the notion of discrimination, i.e. separating one particular object from the other objects in the scene. Over the course of many such interactions, the learner incrementally and in real-time builds a complete repertoire of concepts that is functional in the world. A video of the demonstration can be found at https://ehai.ai. vub.ac.be/demos/interactive-concept-learning.

UR - http://www.scopus.com/inward/record.url?scp=85075040944&partnerID=8YFLogxK

M3 - Meeting abstract (Book)

VL - 2491

T3 - CEUR Workshop Proceedings

BT - Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)

A2 - Beuls, Katrien

A2 - Bogaerts, Bart

A2 - Bontempi, Gianluca

A2 - Geurts, Pierre

A2 - Harley, Nick

A2 - Lebichot, Bertrand

A2 - Lenaerts, Tom

A2 - Louppe, Gilles

A2 - Van Eecke, Paul

PB - CEUR Workshop Proceedings

T2 - BNAIC 2019

Y2 - 7 November 2019 through 8 November 2019

ER -

Nevens J, Van Eecke P, Beuls K. Interactive Learning of Grounded Concepts. In Beuls K, Bogaerts B, Bontempi G, Geurts P, Harley N, Lebichot B, Lenaerts T, Louppe G, Van Eecke P, redacteurs, Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019). Vol. 2491. CEUR Workshop Proceedings. 2019. (CEUR Workshop Proceedings).