论文信息 - The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge

The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge

We 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.

Lukas Morand | Raoul Heese | Michal Walczak | Dirk Helm | Michael Bortz

[1] Rolf Mahnken,et al. Identification of Material Parameters for Constitutive Equations , 2004 .

[2] D. Helm. Stress computation in finite thermoviscoplasticity , 2006 .

[3] C. Bishop. Mixture density networks , 1994 .

[4] Joseph N. Wilson,et al. Twenty Years of Mixture of Experts , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[5] Lukas Morand,et al. A mixture of experts approach to handle ambiguities in parameter identification problems in material modeling , 2019, Computational Materials Science.