Neural Control for Rolling Mills: Incorporating Domain Theories to Overcome Data Deficiency

Martin Röscheisen, Reimar Hofmann, Volker Tresp

Abstract

In a Bayesian framework, we give a principled account of how domain(cid:173) specific prior knowledge such as imperfect analytic domain theories can be optimally incorporated into networks of locally-tuned units: by choosing a specific architecture and by applying a specific training regimen. Our method proved successful in overcoming the data deficiency problem in a large-scale application to devise a neural control for a hot line rolling mill. It achieves in this application significantly higher accuracy than optimally-tuned standard algorithms such as sigmoidal backpropagation, and outperforms the state-of-the-art solution.
BibTeX
@inproceedings{roscheisen1991neural,
  author = {Martin Röscheisen and Reimar Hofmann and Volker Tresp},
  title = {{Neural Control for Rolling Mills: Incorporating Domain Theories to Overcome Data Deficiency}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {1991},
}
Figure