Using FCA for Encoding of Closure Operators into Neural Networks
From International Center for Computational Logic
Using FCA for Encoding of Closure Operators into Neural Networks
Sebastian RudolphSebastian Rudolph
Using FCA for Encoding of Closure Operators into Neural Networks
- ISBN: 978-3-540-73680-6
- ISSN: 0302-9743
- Download
Sebastian Rudolph
Using FCA for Encoding of Closure Operators into Neural Networks
In Uta Priss, Simon Polovina, Richard Hill, eds., Conceptual Structures: Knowledge Architectures for Smart Applications, Proc. ICCS 2007, volume 4604 of LNAI, 321 -- 332, July 2007. Springer-Verlag
Using FCA for Encoding of Closure Operators into Neural Networks
In Uta Priss, Simon Polovina, Richard Hill, eds., Conceptual Structures: Knowledge Architectures for Smart Applications, Proc. ICCS 2007, volume 4604 of LNAI, 321 -- 332, July 2007. Springer-Verlag
- KurzfassungAbstract
After decades of concurrent development of symbolic and connectionist methods, recent years have shown intensifying efforts of integrating those two paradigms. This paper contributes to the development of methods for transferring present symbolic knowledge into connectionist representations. Motivated by basic ideas from formal concept analysis, we propose two ways of directly encoding closure operators on finite sets in a 3-layered feed forward neural network. - Forschungsgruppe:Research Group: Computational LogicComputational Logic
@inproceedings{R2007,
author = {Sebastian Rudolph},
title = {Using {FCA} for Encoding of Closure Operators into Neural
Networks},
editor = {Uta Priss and Simon Polovina and Richard Hill},
booktitle = {Conceptual Structures: Knowledge Architectures for Smart
Applications, Proc. {ICCS} 2007},
series = {LNAI},
volume = {4604},
publisher = {Springer-Verlag},
year = {2007},
month = {July},
pages = {321 -- 332}
}