Open AccessFree-lunch learning and directional distributions in artificial neural networks
Author(s) -
P. E. Jupp,
James V. Stone
Publication year - 2008
Publication title -
acta et commentationes universitatis tartuensis de mathematica./acta et commentationes universitatis tartuensis de mathematica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.276
H-Index - 6
eISSN - 2228-4699
pISSN - 1406-2283
DOI - 10.12697/acutm.2008.12.09
Subject(s) - forgetting , artificial neural network , artificial intelligence , phenomenon , psychology , computer science , statistical physics , cognitive psychology , physics , quantum mechanics
Free-lunch learning (FLL) is a phenomenon in which relearning partially-forgotten mental associations induces recovery of otherassociations. FLL occurs also in artificial neural networks (ANN’s). Two models for forgetting in ANN’s are presented which involve uniform distributions on spheres and Grassmann manifolds. It is shown that these models differ markedly in their amounts of FLL.