Authors: Todorović, Branimir
Stanković, Miomir 
Moraga, Claudio
Title: Derivative free training of recurrent neural networks a comparison of algorithms and architectures
Journal: NCTA 2014 - Proceedings of the International Conference on Neural Computation Theory and Applications
First page: 76
Last page: 84
Issue Date: 1-Jan-2014
Rank: M33
ISBN: 978-989-758-054-3
DOI: 10.5220/0005081900760084
The problem of recurrent neural network training is considered here as an approximate joint Bayesian estimation of the neuron outputs and unknown synaptic weights. We have implemented recursive estimators using nonlinear derivative free approximation of neural network dynamics. The computational efficiency and performances of proposed algorithms as training algorithms for different recurrent neural network architectures are compared on the problem of long term, chaotic time series prediction.
Keywords: Bayesian estimation | Chaotic time series prediction | Nonlinear derivative free estimation | Recurrent neural networks

Show full item record


checked on May 28, 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.