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

Combining Learning Constraints and Numerical Regression

Dorian Šuc and Ivan Bratko (2005) Combining Learning Constraints and Numerical Regression. In: 19th Int. Joint Conf. on Artificial Intelligence, IJCAI-05, 30 July - 5 August 2005, Edinburgh, Scotland.

Download (129Kb)


    Usual numerical learning methods are primarily concerned with finding a good numerical fit to data and often make predictions that do not correspond to qualitative laws in the domain of modelling or expert intuition. In contrast, the idea of $Q^2$ learning is to induce qualitative constraints from training data, and use the constraints to guide numerical regression. The resulting numerical predictions are consistent with a learned qualitative model which is beneficial in terms of explanation of phenomena in the modelled domain, and can also improve numerical accuracy. This paper proposes a method for combining the learning of qualitative constraints with an arbitrary numerical learner and explores the accuracy and explanation benefits of learning monotonic qualitative constraints in a number of domains. We show that $Q^2$ learning can correct for errors caused by the bias of the learning algorithm and discuss the potentials of similar hierarchical learning schemes.

    Item Type: Conference or Workshop Item (Paper)
    Keywords: machine learning, qualitative reasoning, combining classifiers, monotonicity constraints
    Language of Content: English
    Related URLs:
    URLURL Type
    http://ai.fri.uni-lj.si/dorian/pub/papers.htmAlternative location
    http://www.ijcai.orgAlternative location
    http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(id=5162068)Alternative location
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Divisions: Faculty of Computer and Information Science > Artificial Intelligence Laboratory
    Item ID: 179
    Date Deposited: 11 Aug 2005
    Last Modified: 05 Dec 2013 15:18
    URI: http://eprints.fri.uni-lj.si/id/eprint/179

    Actions (login required)

    View Item