RTU Research Information System
Latviešu English

Publikācija: Neo-Fuzzy Encoder and Its Adaptive Learning for Big Data Processing

Publication Type Publication (anonimusly reviewed) in a journal with an international editorial board indexed in other databases
Funding for basic activity State funding for education
Defending: ,
Publication language English (en)
Title in original language Neo-Fuzzy Encoder and Its Adaptive Learning for Big Data Processing
Field of research 2. Engineering and technology
Sub-field of research 2.2 Electrical engineering, Electronic engineering, Information and communication engineering
Authors Yevgeniy Bodyanskiy
Iryna Pliss
Olena Vynokurova
Dmytro Peleshko
Yuriy Rashkevych
Keywords Artificial neural networks, computational intelligence, data compression, machine learning.
Abstract In the paper a two-layer encoder is proposed. The nodes of encoder under consideration are neo-fuzzy neurons, which are characterised by high speed of learning process and effective approximation properties. The proposed architecture of neo-fuzzy encoder has a two-layer bottle neck” structure and its learning algorithm is based on error backpropagation. The learning algorithm is characterised by a high rate of convergence because the output signals of encoder’s nodes (neo-fuzzy neurons) are linearly dependent on the tuning parameters. The proposed learning algorithm can tune both the synaptic weights and centres of membership functions. Thus, in the paper the hybrid neo-fuzzy system-encoder is proposed that has essential advantages over conventional neurocompressors.
DOI: 10.1515/itms-2017-0001
Reference Bodyanskiy, Y., Pliss, I., Vynokurova, O., Peleshko, D., Rashkevych, Y. Neo-Fuzzy Encoder and Its Adaptive Learning for Big Data Processing. Information Technology and Management Science, 2017, 20, pp.6-11. ISSN 2255-9086. e-ISSN 2255-9094. Available from: doi:10.1515/itms-2017-0001
ID 26858