Je serai présent lors de la conférence ICANN 2010 qui aura lieu en Grèce.
Site de la conférence : http://delab.csd.auth.gr/icann2010/
J’y présenterai mes derniers travaux sur les réseaux de neurones portant sur l’équilibrage des différents temps d’apprentissage.
Abstract : The purpose of this work is to further study the relevance of accelerating the
Monte Carlo calculations for the gamma rays external radiotherapy through
feed-forward neural networks. We have previously presented a parallel
incremental algorithm that builds neural networks of reduced size, while
providing high quality approximations of the dose deposit. Our parallel
algorithm consists in a regular decomposition of the initial learning dataset
(also called learning domain) in as much subsets as available
processors. However, the initial learning set presents heterogeneous signal
complexities and consequently, the learning times of regular subsets are very
different. This paper presents an efficient learning domain decomposition
which balances the signal complexities across the processors. As will be
shown, the resulting irregular decomposition allows for important gains in
learning time of the global network.
[ad#Google Adsense]