ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Knowledge gap detection for interactive learning of categorical knowledge

Matjaž Majnik and Matej Kristan and Danijel Skočaj (2013) Knowledge gap detection for interactive learning of categorical knowledge. In: 18th Computer Vision Winter Workshop, February 4-6, 2013, Hernstein, Austria.

PDF - Published Version
Download (308Kb)


    In interactive machine learning the process of labeling training instances and introducing them to the learner may be expensive in terms of human effort and time. In this paper we present different strategies for detecting gaps in the learner's knowledge and communicating these gaps to the teacher. These strategies are considered from the viewpoint of extrospective and introspective behavior of the learner - this new perspective is also the main contribution of our paper. The experimental results indicate that the analyzed strategies are successful in reducing the number of training instances required to reach the needed recognition rate. Such a facilitation may be an important step towards the broader use of interactive autonomous systems.

    Item Type: Conference or Workshop Item (Paper)
    Keywords: active learning, artificial cognitive systems, transfer of categorical knowledge, interactive learning, human-robot interaction, detection of knowledge gaps, introspection and extrospection
    Related URLs:
    URLURL Type
    http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(id=9662548)Alternative location
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Divisions: Faculty of Computer and Information Science > Visual Cognitive Systems Laboratory
    Item ID: 2034
    Date Deposited: 03 May 2013 21:18
    Last Modified: 05 Dec 2013 13:59
    URI: http://eprints.fri.uni-lj.si/id/eprint/2034

    Actions (login required)

    View Item