| Autor: |
Beck, Florian, Fürnkranz, Johannes |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
2nd Workshop on Deep Continuous-Discrete Machine Learning (DeCoDeML), ECML-PKDD 2020, Ghent, Belgium |
| Druh dokumentu: |
Working Paper |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
