Reasoning About Time and Knowledge in Neural Symbolic Learning Systems
Abstract
We show that temporal logic and combinations of temporal logics and modal logics of knowledge can be effectively represented in ar(cid:173) tificial neural networks. We present a Translation Algorithm from temporal rules to neural networks, and show that the networks compute a fixed-point semantics of the rules. We also apply the translation to the muddy children puzzle, which has been used as a testbed for distributed multi-agent systems. We provide a complete solution to the puzzle with the use of simple neural networks, capa(cid:173) ble of reasoning about time and of knowledge acquisition through inductive learning.
Cite
Text
Garcez and Lamb. "Reasoning About Time and Knowledge in Neural Symbolic Learning Systems." Neural Information Processing Systems, 2003.Markdown
[Garcez and Lamb. "Reasoning About Time and Knowledge in Neural Symbolic Learning Systems." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/garcez2003neurips-reasoning/)BibTeX
@inproceedings{garcez2003neurips-reasoning,
title = {{Reasoning About Time and Knowledge in Neural Symbolic Learning Systems}},
author = {Garcez, Artur and Lamb, Luis C.},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {921-928},
url = {https://mlanthology.org/neurips/2003/garcez2003neurips-reasoning/}
}