Raoul Heese, Michał Walczak, Lukas Morand, Dirk Helm, Michael Bortz
Published 2019-07-24Version 1
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.
Comments: International Conference on Artificial Neural Networks (ICANN) 2019
IL-Net: Using Expert Knowledge to Guide the Design of Furcated Neural Networks
COKE: Causal Discovery with Chronological Order and Expert Knowledge in High Proportion of Missing Manufacturing Data
Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
![QR code for arXiv:1907.11105 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)