Rethinking Sigma’s Graphical Architecture: An Extension to Neural Networks (bibtex)
by Paul S. Rosenbloom, Abram Demski, Volkan Ustun
Abstract:
The status of Sigma’s grounding in graphical models is challenged by the ways in which their semantics has been violated while incorporating rule-based reasoning into them. This has led to a rethinking of what goes on in its graphical architecture, with results that include a straightforward extension to feedforward neural networks (although not yet with learning).
Reference:
Rethinking Sigma’s Graphical Architecture: An Extension to Neural Networks (Paul S. Rosenbloom, Abram Demski, Volkan Ustun), In International Conference on Artificial General Intelligence, Springer, volume 9782, 2016.
Bibtex Entry:
@inproceedings{rosenbloom_rethinking_2016,
	address = {New York, NY},
	title = {Rethinking {Sigma}’s {Graphical} {Architecture}: {An} {Extension} to {Neural} {Networks}},
	volume = {9782},
	isbn = {978-3-319-41649-6},
	url = {http://link.springer.com/chapter/10.1007/978-3-319-41649-6_9},
	doi = {10.1007/978-3-319-41649-6_9},
	abstract = {The status of Sigma’s grounding in graphical models is challenged by the ways in which their semantics has been violated while incorporating rule-based reasoning into them. This has led to a rethinking of what goes on in its graphical architecture, with results that include a straightforward extension to feedforward neural networks (although not yet with learning).},
	booktitle = {International {Conference} on {Artificial} {General} {Intelligence}},
	publisher = {Springer},
	author = {Rosenbloom, Paul S. and Demski, Abram and Ustun, Volkan},
	month = jul,
	year = {2016},
	keywords = {CogArch, Virtual Humans, UARC},
	pages = {84--94}
}
Powered by bibtexbrowser