2 papers
cs.LG2025
Sharing Knowledge without Sharing Data: Stitches can improve ensembles of disjointly trained models
Arthur Guijt, Dirk Thierens, Ellen Kerkhof +3
Deep learning has been shown to be very capable at performing many real-world tasks. However, this performance is often dependent on the presence of large and varied datasets. In s…
cs.NE2025
The Pitfalls and Potentials of Adding Gene-invariance to Optimal Mixing
Anton Bouter, Dirk Thierens, Peter A. N. Bosman
Optimal Mixing (OM) is a variation operator that integrates local search with genetic recombination. EAs with OM are capable of state-of-the-art optimization in discrete spaces, of…