A Fully Connectionist Model Generator for Covered First-Order Logic Programs

Abstract

We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples, we embed the associated semantic operator into a feed-forward network and train the network using the examples. This results in the learning of first-order knowledge while damaged or noisy data is handled gracefully.

Cite

Text

Bader et al. "A Fully Connectionist Model Generator for Covered First-Order Logic Programs." International Joint Conference on Artificial Intelligence, 2007.

Markdown

[Bader et al. "A Fully Connectionist Model Generator for Covered First-Order Logic Programs." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/bader2007ijcai-fully/)

BibTeX

@inproceedings{bader2007ijcai-fully,
  title     = {{A Fully Connectionist Model Generator for Covered First-Order Logic Programs}},
  author    = {Bader, Sebastian and Hitzler, Pascal and Hölldobler, Steffen and Witzel, Andreas},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2007},
  pages     = {666-671},
  url       = {https://mlanthology.org/ijcai/2007/bader2007ijcai-fully/}
}