Spectra of the Spike-Flow Graphs in Geometrically Embedded Neural Networks
| dc.contributor.author | Piersa, Jarosław | |
| dc.contributor.author | Schreiber, Tomasz | |
| dc.date.accessioned | 2014-02-08T17:48:21Z | |
| dc.date.available | 2014-02-08T17:48:21Z | |
| dc.date.issued | 2012-04-29 | |
| dc.description | Full article available at Springerlink: http://link.springer.com/chapter/10.1007%2F978-3-642-29347-4_17 DOI: 10.1007/978-3-642-29347-4_17 | pl |
| dc.description.abstract | In this work we study a simplified model of a neural activity flow in networks, whose connectivity is based on geometrical embedding, rather than being lattices or fully connected graphs. We present numerical results showing that as the spectrum (set of eigenvalues of adjacency matrix) of the resulting activity-based network develops a scale-free dependency. Moreover it strengthens and becomes valid for a wider segment along with the simulation progress, which implies a highly organised structure of the analysed graph. | pl |
| dc.description.sponsorship | The work has been partially supported by National Research Centre research grant UMO-2011/01/N/ST6/01931. The author is grateful to PL-GridProject staff and help-line for computing resources. | pl |
| dc.identifier.citation | Lecture Notes in Computer Science Volume 7267, 2012, pp 143-151 | pl |
| dc.identifier.issn | 0302-9743 | |
| dc.identifier.uri | http://repozytorium.umk.pl/handle/item/1674 | |
| dc.language.iso | eng | pl |
| dc.publisher | Springer Berlin Heidelberg | pl |
| dc.relation.ispartofseries | Artificial Intelligence and Soft Computing; | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | geometric neural networks | pl |
| dc.subject | graph spectrum | pl |
| dc.subject | scale-freeness | pl |
| dc.title | Spectra of the Spike-Flow Graphs in Geometrically Embedded Neural Networks | pl |
| dc.type | info:eu-repo/semantics/conferenceObject | pl |