A novel approach to error function minimization for feedforward neural networks
High Energy Physics - Experiment
2010-11-01 v2
Abstract
Feedforward neural networks with error backpropagation (FFBP) are widely applied to pattern recognition. One general problem encountered with this type of neural networks is the uncertainty, whether the minimization procedure has converged to a global minimum of the cost function. To overcome this problem a novel approach to minimize the error function is presented. It allows to monitor the approach to the global minimum and as an outcome several ambiguities related to the choice of free parameters of the minimization procedure are removed.
Cite
@article{arxiv.hep-ex/9501007,
title = {A novel approach to error function minimization for feedforward neural networks},
author = {Ralph Sinkus},
journal= {arXiv preprint arXiv:hep-ex/9501007},
year = {2010}
}
Comments
11 pages, latex, 3 figures appended as uuencoded file