The training of feedforward networks using conventional Badcrpopagation algorithm is plagued by poor convergence and misadjustment.In this paper, introduce the Multiple Eztended Kalman algorithm (MEKA) to train feedforward networks. It is based on the idea of partitioning the global problem of finding the weights into a set of manageable nonlinear subproblems. The algorithm is local at the neuron level. We demonstrate the superiority of MEKA over the Global Extended K a h a n algorithm in terms of convergence and quality of solution obtained on two benchmark problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.