3 papers
stat.ML2019
Stochastic Gradient Trees
Henry Gouk, Bernhard Pfahringer, Eibe Frank
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 le…
stat.ML2018
MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes
Henry Gouk, Bernhard Pfahringer, Eibe Frank +1
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 con…
stat.ML2018
Regularisation of Neural Networks by Enforcing Lipschitz Continuity
Henry Gouk, Eibe Frank, Bernhard Pfahringer +1
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…