Abstract
This paper proposes a novel method for supervised optimization of cellular automata rules using curriculum learning. The optimized edge detector manages to generalize a rule from synthetic data that is applicable to magnetic resonance images, removing the need for manual annotation of medical data. The method achieves competitive results with classical edge detectors on our test set and may be incorporated in computer-aided diagnosis systems.
Citare
Dumitru D., Andreica A., Dioșan L., Balint Z., Evolutionary curriculum learning approach for transferable cellular automata rule optimizationGECCO 2019 (Proceedings of the Genetic and Evolutionary Computation Conference Companion, ACM), , 63-64, 2020