Florian Beck, Johannes Fürnkranz,
"An Investigation into Mini-Batch Rule Learning"
, in Kristian Kersting and Stefan Kramer and Zahra Ahmadi: Proceedings of the 2nd Workshop on Deep Continuous-Discrete Machine Learning (DeCoDeML), 2020
An Investigation into Mini-Batch Rule Learning
Sprache des Titels:
Proceedings of the 2nd Workshop on Deep Continuous-Discrete Machine Learning (DeCoDeML)
We investigate whether it is possible to learn rule sets efficiently in a network structure with a single hidden layer using iterative refinements over mini-batches of examples. A first rudimentary version shows an acceptable performance on all but one dataset, even though it does not yet reach the performance levels of RIPPER.