Encouraging Networks Modularity by Seeding Motifs

Shuguang Li, Jianping Yuan, Juan Cristóbal Zagal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We propose a motifs seeding method to encourage the emergence of modular structure during network evolution. Previous studies fail to trigger modularity on freeform evolving ANNs either when varying environmental factors or the evolutionary process itself. We extracted statistical profiles of 3-node and 4-node motifs from evolved networks, and then generated new networks by seeding the most useful 3-node motif (feed-forward loop, ID:38). A series of retina recognition experiments was conducted using the seeded networks. The performance of different algorithms was measured. Our results indicate that modularity could be encouraged under certain conditions. We were able to build networks meeting a desired Z-score.

Original languageEnglish
Title of host publicationECAL 2011
Subtitle of host publicationThe 11th European Conference on Artificial Life
PublisherMIT Press Journals
ISBN (Electronic)9780262297141
DOIs
StatePublished - 2011
Event11th European Conference on Artificial Life, ECAL 2011 - Paris, France
Duration: 8 Aug 201112 Aug 2011

Publication series

NameECAL 2011: The 11th European Conference on Artificial Life

Conference

Conference11th European Conference on Artificial Life, ECAL 2011
Country/TerritoryFrance
CityParis
Period8/08/1112/08/11

Fingerprint

Dive into the research topics of 'Encouraging Networks Modularity by Seeding Motifs'. Together they form a unique fingerprint.

Cite this