SELF-SIMILARITY IN NETWORKS THAT LEARN BY EXAMPLES

Authors
VANDENBROECK C BEX GJ
Citation
C. Vandenbroeck et Gj. Bex, SELF-SIMILARITY IN NETWORKS THAT LEARN BY EXAMPLES, Philosophical magazine. B. Physics of condensed matter.Statistical mechanics, electronic, optical and magnetic, 77(5), 1998, pp. 1479-1486
Citations number
27
Categorie Soggetti
Physics, Applied",Mechanics,"Physics, Condensed Matter","Material Science
Journal title
Philosophical magazine. B. Physics of condensed matter.Statistical mechanics, electronic, optical and magnetic → ACNP
ISSN journal
13642812
Volume
77
Issue
5
Year of publication
1998
Pages
1479 - 1486
Database
ISI
SICI code
1364-2812(1998)77:5<1479:SINTLB>2.0.ZU;2-X
Abstract
We illustrate how a multifractal analysis, based on numerical results for Boolean networks and analytic results for neural networks, allows us to gain insight into the mechanism by which networks can learn by e xamples.