2D-Neo-Fuzzy Neuron and Its Adaptive Learning

2018
Yevgeniy Bodyanskiy, Olena Vynokurova, Valentyna Volkova, Olena Boiko

In the paper, 2D-neo-fuzzy neuron (NFN) is presented. It is a generalization of the traditional NFN for data in matrix form. 2D-NFN is based on the matrix adaptive bilinear model with an additional fuzzification layer. It reduces the number of adjustable synaptic weights in comparison with traditional systems. For its learning, optimized adaptive procedures with filtering and tracking properties are proposed. 2D-NFN can be effectively used for image processing, data reduction, and restoration of non-stationary signals presented as 2D-sequences.

Keywords
2D network, data mining, hybrid systems, neo-fuzzy neuron
DOI
10.7250/itms-2018-0003
Hyperlink
https://itms-journals.rtu.lv/article/view/itms-2018-0003

Bodyanskiy, Y., Vynokurova, O., Volkova, V., Boiko, O. 2D-Neo-Fuzzy Neuron and Its Adaptive Learning. Information Technology and Management Science, 2018, Vol. 21, No. 1, pp.24-28. ISSN 2255-9086. e-ISSN 2255-9094. Available from: doi:10.7250/itms-2018-0003

Publication language
English (en)