Authors: Todorović, Branimir
Moraga, Claudio
Stanković, Miomir
Title: Sequential Bayesian estimation of recurrent neural networks
Journal: Studies in Fuzziness and Soft Computing
Volume: 349
First page: 173
Last page: 199
Issue Date: 1-Oct-2017
ISSN: 14349922
DOI: 10.1007/978-3-319-48317-7_11
© Springer International Publishing AG 2017. This is short overview of the authors' research in the area of the sequential or recursive Bayesian estimation of recurrent neural networks. Our approach is founded on the joint estimation of synaptic weights, neuron outputs and structure of the recurrent neural networks. Joint estimation enables generalization of the training heuristic known as teacher forcing, which improves the training speed, to the sequential training on noisy data. By applying Gaussian mixture approximation of relevant probability density functions, we have derived training algorithms capable to deal with non-Gaussian (multi modal or heavy tailed) noise on training samples. Finally, we have used statistics, recursively updated during sequential Bayesian estimation, to derive criteria for growing and pruning of synaptic connections and hidden neurons in recurrent neural networks.

Show full item record


checked on Jul 14, 2024

Page view(s)

checked on May 9, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.