Publication details

Combining multiple classifiers in probabilistic neural networks

Conference Paper (international conference)

Grim Jiří, Kittler J., Pudil Pavel, Somol Petr


serial: Multiple Classifier Systems, p. 157-166 , Eds: Kittler J., Roli F.

publisher: Springer, (Berlin 2000)

edition:

action: First International Workshop MCS 2000, (Cagliari, IT, 21.06.2000-23.06.2000)

research: AV0Z1075907

project(s): IAA2075703, GA AV, VS96063, MŠMT, KSK1075601, GA AV

abstract (eng):

The paper summarizes main features of a new probabilistic approach to neural networks in the framework of statistical pattern recognition. Assuming approximation of class-conditional distributions by finite mixtures we identify formal neurons with the components of finite mixtures and therefore the EM algorithm can be used to optimize the parameters of neurons. In order to prevent the arising information loss we propose a parallel use of the output variables to design the Bayesian classifier.

Cosati: 12B, 09K

RIV: BB