An Investigation into Mini-Batch Rule Learning

06/18/2021

∙

by   Florian Beck, et al.

∙

0

∙

share

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.