Projects per year
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019) |
Editors | Katrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, Paul Van Eecke |
Publisher | CEUR Workshop Proceedings |
Number of pages | 2 |
Volume | 2491 |
ISBN (Electronic) | 1613-0073 |
Publication status | Published - 6 Nov 2019 |
Event | BNAIC 2019 - Brussels, Belgium Duration: 7 Nov 2019 → 8 Nov 2019 |
Publication series
Name | CEUR Workshop Proceedings |
---|---|
ISSN (Print) | 1613-0073 |
Conference
Conference | BNAIC 2019 |
---|---|
Country/Territory | Belgium |
City | Brussels |
Period | 7/11/19 → 8/11/19 |
Fingerprint
Dive into the research topics of 'Interactive Learning of Grounded Concepts'. Together they form a unique fingerprint.Projects
- 1 Finished
-
FWOSB64: Hybrid AI for mapping between natural language utterances and their executable meanings
Nevens, J., Beuls, K. & Nowe, A.
1/01/19 → 31/12/22
Project: Fundamental