Projects per year
Abstract
Autonomous agents perceive the world through streams of continuous sensori-motor data. Yet, in order to reason and communicate about their environment, agents need to be able to distill meaningful concepts from their raw observations. Most current approaches that bridge between the continuous and symbolic domain are using deep learning techniques. While these approaches often achieve high levels of accuracy, they rely on large amounts of training data, and the resulting models lack transparency, generality, and adaptivity. In this paper, we introduce a novel methodology for grounded concept learning. In a tutor-learner scenario, the method allows an agent to construct a conceptual system in which meaningful concepts are formed by discriminative combinations of prototypical values on human-interpretable feature channels. We evaluate our approach on the CLEVR dataset, using features that are either simulated or extracted using computer vision techniques. Through a range of experiments, we show that our method allows for incremental learning, needs few data points, and that the resulting concepts are general enough to be applied to previously unseen objects and can be combined compositionally. These properties make the approach well-suited to be used in robotic agents as the module that maps from continuous sensory input to grounded, symbolic concepts that can then be used for higher-level reasoning tasks.
Original language | English |
---|---|
Title of host publication | Proceedings of the 32nd Benelux Conference on Artificial Intelligence (BNAIC 2020) and the 29th Belgian Dutch Conference on Machine Learning (Benelearn 2020) |
Editors | Lu Cao, Walter Kosters, Jefrey Lijffijt |
Place of Publication | Leiden, the Netherlands |
Pages | 388-389 |
Number of pages | 2 |
Volume | 7 |
DOIs | |
Publication status | Published - 26 Jun 2020 |
Event | 32nd Benelux Conference on Artificial Intelligence/Belgian-Dutch Conference on Machine Learning - Leiden, Netherlands Duration: 19 Nov 2020 → 20 Nov 2020 https://bnaic.liacs.leidenuniv.nl |
Publication series
Name | Frontiers in robotics and AI |
---|---|
Publisher | Frontiers Media |
ISSN (Print) | 2296-9144 |
Conference
Conference | 32nd Benelux Conference on Artificial Intelligence/Belgian-Dutch Conference on Machine Learning |
---|---|
Abbreviated title | BNAIC/BeneLearn 2020 |
Country/Territory | Netherlands |
City | Leiden |
Period | 19/11/20 → 20/11/20 |
Internet address |
Bibliographical note
Funding Information:Funding. The research reported in this paper was funded by the European Union's Horizon 2020 research and innovation programme under grant agreement no. 732942 and the Flemish Government under the Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen programme. JN was supported by the Research Foundation Flanders (FWO) through grant 1SB6219N.
Publisher Copyright:
© Copyright © 2020 Nevens, Van Eecke and Beuls.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
Fingerprint
Dive into the research topics of 'From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning'. 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
Activities
- 1 Talk or presentation at a conference
-
From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning
Jens Nevens (Speaker)
19 Nov 2020Activity: Talk or presentation › Talk or presentation at a conference