Heese, R.R.HeeseWalczak, M.M.WalczakMorand, L.L.MorandHelm, D.D.HelmBortz, M.M.Bortz2022-03-142022-03-142019https://publica.fraunhofer.de/handle/publica/40528810.1007/978-3-030-30493-5_38We address a non-unique parameter fitting problem in the context of material science. In particular, we propose to resolve ambiguities in parameter space by augmenting a black-box artificial neural network (ANN) model with two different levels of expert knowledge and benchmark them against a pure black-box model.enexpert knowledgemixture of expertscustom loss003620006519conference paper