caa a22 4500 605519382 CHVBK 20210128100730.0 cr unu---uuuuu 210128e20150301xx s 000 0 eng 10.1007/s10559-015-9710-4 doi (NATIONALLICENCE)springer-10.1007/s10559-015-9710-4 Skorohod B. Sevastopol National Technical University, Sevastopol, Ukraine aut Learning Algorithms for Neural Networks and Neuro-Fuzzy Systems with Separable Structures [Elektronische Daten] [B. Skorohod] This article considers the problem of training neural networks and neuro-fuzzy systems, which lead to separable models, i.e., structures nonlinear with respect to some unknown parameters and linear with respect to others. New algorithms for training them are proposed that are based on a nonlinear optimization problem including a priori information only on nonlinear input parameters. It is assumed that this information can be obtained from a training set, the distribution of a generating set, or linguistic information. To solve the problem, the Gauss-Newton method with linearization in the vicinity of the last estimate, asymptotic representations of the pseudo-inverse of perturbed matrices, and separable structures of models are used. The obtained algorithms have the following important properties: they do not require the selection of initial values of linearly entering parameters, which can lead to divergence, but, at the same time, it is not necessary to find partial derivatives of a projection matrix; they can be used in serial and batch processing; well-known algorithms are obtained from them as special cases, and a simulation has shown that the proposed algorithms can outperform the former in accuracy and convergence rate. Springer Science+Business Media New York, 2015 separable regression nationallicence neural network nationallicence neuro-fuzzy system nationallicence learning algorithm nationallicence Cybernetics and Systems Analysis Springer US; http://www.springer-ny.com 51/2(2015-03-01), 173-186 1060-0396 51:2<173 2015 51 10559 https://doi.org/10.1007/s10559-015-9710-4 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s10559-015-9710-4 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Skorohod B. Sevastopol National Technical University, Sevastopol, Ukraine aut NATIONALLICENCE 773 0- Cybernetics and Systems Analysis Springer US; http://www.springer-ny.com 51/2(2015-03-01), 173-186 1060-0396 51:2<173 2015 51 10559