Browsing by Author "Gouk, Henry"

Now showing items 6-9 of 9

  • Learning Distance Metrics for Multi-Label Classification

    Gouk, Henry; Pfahringer, Bernhard; Cree, Michael J. (2016)
    Distance metric learning is a well studied problem in the field of machine learning, where it is typically used to improve the accuracy of instance based learning techniques. In this paper we propose a distance metric ...
  • MaxGain: Regularisation of neural networks by constraining activation magnitudes

    Gouk, Henry; Pfahringer, Bernhard; Frank, Eibe; Cree, Michael J. (Springer, 2019)
    Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, ...
  • Regularisation of neural networks by enforcing Lipschitz continuity

    Gouk, Henry; Frank, Eibe; Pfahringer, Bernhard; Cree, Michael J. (Springer, 2020)
    We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant—for ...
  • Stochastic gradient trees

    Gouk, Henry; Pfahringer, Bernhard; Frank, Eibe (PMLR, 2019)
    We present an algorithm for learning decision trees using stochastic gradient information as the source of supervision. In contrast to previous approaches to gradient-based tree learning, our method operates in the incremental ...