Network Structuring and Training Using Rule-Based Knowledge

Abstract

We demonstrate in this paper how certain forms of rule-based knowledge can be used to prestructure a neural network of nor(cid:173) malized basis functions and give a probabilistic interpretation of the network architecture. We describe several ways to assure that rule-based knowledge is preserved during training and present a method for complexity reduction that tries to minimize the num(cid:173) ber of rules and the number of conjuncts. After training the refined rules are extracted and analyzed.

Cite

Text

Tresp et al. "Network Structuring and Training Using Rule-Based Knowledge." Neural Information Processing Systems, 1992.

Markdown

[Tresp et al. "Network Structuring and Training Using Rule-Based Knowledge." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/tresp1992neurips-network/)

BibTeX

@inproceedings{tresp1992neurips-network,
  title     = {{Network Structuring and Training Using Rule-Based Knowledge}},
  author    = {Tresp, Volker and Hollatz, Jürgen and Ahmad, Subutai},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {871-878},
  url       = {https://mlanthology.org/neurips/1992/tresp1992neurips-network/}
}