Free-lunch learning and directional distributions in artificial neural networks

Authors

  • Peter E. Jupp University of St Andrews
  • James V. Stone University of Sheffield

DOI:

https://doi.org/10.12697/ACUTM.2008.12.09

Keywords:

Grassmann manifold, isotropy, sphere, uniform distribution

Abstract

Free-lunch learning (FLL) is a phenomenon in which relearning partially-forgotten mental associations induces recovery of other
associations. 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.

Downloads

Download data is not yet available.

Downloads

Published

2008-12-31

Issue

Section

Articles