A Developmental Approach to Concept Learning

Liesl Wigand, Monica Nicolescu, Mircea Nicolescu


The ability to learn new concepts is essential for any robot to be successful in real-world applications. This is due to the fact that it is impractical for a robot designer to pre-endow it with all the concepts that it would encounter during its operational lifetime. In this context, it becomes necessary that the robot is able to acquire new concepts, in a real-world context, from cues provided in natural, unconstrained interactions, similar to a human-teaching approach. However, existing approaches on concept learning from visual images and abstract concept learning address this problem in a manner that makes them unsuitable for learning in an embodied, real-world environment. This paper presents a developmental approach to concept learning. The proposed system learns abstract, generic features of objects and associates words from sentences referring to those objects with the features, thus providing a grounding for the meaning of the words. The method thus allows the system to later identify such features in previously unseen images. The paper presents results obtained on data acquired with a Kinect camera and on synthetic images.


  1. Bloom, P. (2002). How Children Learn the Meaning of Words. MIT Press.
  2. Bogdan Rusu, R. and Cousins, S. (2011). 3d is here: Point cloud library (pcl). In IEEE International Robotics and Automation (ICRA).
  3. Brodley, C. E. and Friedl, M. (1999). Identifying mislabeled training data. Journal of Artificial Intelligence Research, 11:131-167.
  4. Coates, A., Lee, H., and Ng, A. Y. (2010). An analysis of single-layer networks in unsupervised feature learning. In Advances in Neural Information Processing Systems.
  5. Feldman, J. (2003). The simplicity principle in human concept learning. Current Directions in Psychological Science, 12(6):227-232.
  6. Hoffman, A. B. and Murphy, G. L. (2006). Category dimensionality and feature knowledge: When more features are learned as easily as fewer. Journal of Experimental Psychology: Learning, Memory, and Cognition, 32(3):301-315.
  7. Horst, J., Oakes, L., and Madole, K. (2005). What does it look like and what can it do? category structure influences how infants categorize. Child Development, 76(3):614-631.
  8. Huang, F. J. and LeCun, Y. (2006). Large-scale learning with svm and convolutional nets for generic object characterization. In Proc., IEEE Conf. on Computer Vision and Pattern Recognition.
  9. Kaplan, A. and Murphy, G. (200). Category learning with minimal prior knowledge. Journal of Experimental Psychology: Learning, Memory and Cognition, 26(4):829-846.
  10. Khan, S. S. and Madden, M. G. (2010). A survey of recent trends in one class classification. In Articial Intelligence and Cognitive Science - 20th Irish Conference.
  11. Lai, K., Bo, L., Ren, X., and Fox, D. (2012). Rgb-d (kinect) object database. http://www.cs.washington.edu/rgbddataset/index.html.
  12. Lew, M., Sebe, N., Djeraba, C., and Jain, R. (2006). Content-based multimedia information retrieval: State of the art challenges. ACM Transactions on Multimedia Computing, COmmunications, and Applications.
  13. Lungarella, M., Metta, G., Pfeifer, R., and Sandini, G. (2003). Developmental robotics: A survey. Connection Science, 15:151-190.
  14. Masci, J., Meier, U., Cires¬łan, D., and Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. In International Conference on Artificial Neural Networks.
  15. Mayor, J. and Plunkett, K. (2008). Learning to associate object categories and label categories: A self-organising model. In Proceedings of the 30th annual conference of the Cognitive Science Society, pages 697-702.
  16. Pedregosa, F., Varoquaux, G., Granfort, A., Michel, V., Thirion, B., Grisel, O., M., B., Prettenhoffer, P., and et. al. (2011). Scikit-learn: machine learning in python. Journal of Machine Learning Research, 12:2825-283.
  17. Piater, J. and Grupen, R. (2000). Constructive feature learning and the development of visual expertise. In Proc., Intl. Conf. on Machine Learning, Stanford, CA. Morgan Kaufmann.
  18. Pinker, S. (2007). The Language Instinct. Harper Perennial Modern Classics, New York.
  19. Scholl, B. (2005). The innate mind: structure and contents. Oxford University Press.
  20. Schyns, P., Goldstone, R., and Thibaut, J.-P. (1998). The development of features in object concepts. Behavioral and Brain Sciences, 21(1):1-54.
  21. Tenebaum, J. B., de Silva, V., and Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290:2319-1323.
  22. Uzwyshyn, R. (2009). An arbitrage oppurtunity for image search and retrieval. Bulletin for the American Society for Information Science and Technology, 35.
  23. Wolfgang Einhauser, Christoph Kayser, K. K. and Konig, P. (2002). Learning multiple feature representations from natural image sequences. In Proc., Intl. Conf. on Artificial Neural Networks.
  24. Yang, Z. and Kuo, J. (2000). Learning image similarities and categories from content analysis and relevance feedback. In Proc., ACM workshops on Multimedia, pages 175-178.

Paper Citation

in Harvard Style

Wigand L., Nicolescu M. and Nicolescu M. (2013). A Developmental Approach to Concept Learning . In Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-71-6, pages 337-344. DOI: 10.5220/0004483803370344

in Bibtex Style

author={Liesl Wigand and Monica Nicolescu and Mircea Nicolescu},
title={A Developmental Approach to Concept Learning},
booktitle={Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},

in EndNote Style

JO - Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - A Developmental Approach to Concept Learning
SN - 978-989-8565-71-6
AU - Wigand L.
AU - Nicolescu M.
AU - Nicolescu M.
PY - 2013
SP - 337
EP - 344
DO - 10.5220/0004483803370344