A Hybrid Neuro-Fuzzy Element: A New Structural Node for Evolving Neuro-Fuzzy Systems

A modification of the structure for a neurofuzzy unit was offered which is generally a hybrid system that combines nonlinear synapses and an activation function to form the hybrid system's output value. The introduced neurofuzzy element is specifically an extension of the common neo-fuzzy neuron which is upgraded at the expense of application of an additional (contracting) activation function. A particular robust learning procedure is also considered for this case that makes it possible to reduce errors while processing data containing abnormal observations.

[1]  Ivan Izonin,et al.  Model and Principles for the Implementation of Neural-Like Structures Based on Geometric Data Transformations , 2018 .

[2]  Oleksii K. Tyshchenko,et al.  An Extended Neo-Fuzzy Neuron and its Adaptive Learning Algorithm , 2016, ArXiv.

[3]  Ivan Izonin,et al.  Learning-based image super-resolution using weight coefficients of synaptic connections , 2015, 2015 Xth International Scientific and Technical Conference "Computer Sciences and Information Technologies" (CSIT).

[4]  Daniel Graupe,et al.  Principles of Artificial Neural Networks , 2018, Advanced Series in Circuits and Systems.

[5]  Takeshi Yamakawa,et al.  Soft Computing Based Signal Prediction, Restoration, and Filtering , 1997 .

[6]  Daniel Graupe.  DEEP LEARNING NEURAL NETWORKS: DESIGN AND CASE STUDIES , 2016 .

[7]  Oleksii K. Tyshchenko,et al.  A deep cascade neural network based on extended neo-fuzzy neurons and its adaptive learning algorithm , 2017, 2017 IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON).

[8]  Yevgeniy V. Bodyanskiy,et al.  Robust Learning Algorithm for Networks of Neuro-Fuzzy Units , 2008, SCSS.

[9]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[10]  M.N.S. Swamy,et al.  Neural Networks and Statistical Learning , 2013 .

[11]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[12]  Oleksii K. Tyshchenko,et al.  A hybrid cascade neural network with an optimized pool in each cascade , 2015, Soft Comput..

[13]  Dmytro Peleshko,et al.  Hybrid Generalized Additive Wavelet-Neuro-Fuzzy-System and Its Adaptive Learning , 2016, DepCoS-RELCOMEX.

[14]  Grady Hanrahan,et al.  Artificial Neural Networks in Biological and Environmental Analysis , 2011 .

[15]  Oleksii K. Tyshchenko,et al.  An evolving radial basis neural network with adaptive learning of its parameters and architecture , 2015, Automatic Control and Computer Sciences.

[16]  TSUTOMU MIKI.  Analog Implementation of Neo-Fuzzy Neuron and Its On-board Learning , 1999 .

[17]  Simone Bassis,et al.  Advances in Neural Networks: Computational and Theoretical Issues , 2015, Smart Innovation, Systems and Technologies.

[18]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[19]  Oleksii K. Tyshchenko,et al.  Adaptive learning of an evolving cascade neo-fuzzy system in data stream mining tasks , 2016, Evol. Syst..

[20]  Oleksii K. Tyshchenko,et al.  An Evolving Cascade System Based on A Set Of Neo Fuzzy Nodes , 2016, ArXiv.

[21]  Joanne Quinn,et al.  Book Review: Deep Learning: Engage the World Change the World , 2019, Journal of Catholic Education.

[22]  Yevgeniy Bodyanskiy,et al.  Fast learning algorithm for deep evolving GMDH-SVM neural network in data stream mining tasks , 2016, 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP).

[23]  Bogdan M. Wilamowski,et al.  Intelligent Systems , 2011 .

[24]  Oleksii K. Tyshchenko,et al.  An evolving connectionist system for data stream fuzzy clustering and its online learning , 2017, Neurocomputing.

[25]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[26]  Jesús S. Aguilar-Ruiz,et al.  Knowledge discovery from data streams , 2009, Intell. Data Anal..

[27]  Oleksii K. Tyshchenko,et al.  A hybrid growing ENFN-based neuro-fuzzy system and its rapid deep learning , 2017, 2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT).

[28]  Kenji Suzuki,et al.  Artificial Neural Networks: Architectures and Applications , 2014 .

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Albert Bifet,et al.  MACHINE LEARNING FOR DATA STREAMS , 2018 .

[31]  Cristina Gena,et al.  Artificial intelligence for human computer interaction , 2014, Intelligenza Artificiale.

[32]  Albert Bifet,et al.  Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams , 2010, Frontiers in Artificial Intelligence and Applications.

[33]  Dong Eui Chang,et al.  Deep Neural Networks in a Mathematical Framework , 2018, SpringerBriefs in Computer Science.

[34]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[35]  Ivan Izonin,et al.  Learning-Based Image Scaling Using Neural-Like Structure of Geometric Transformation Paradigm , 2018 .

[36]  Ramesh C. Jain,et al.  A robust backpropagation learning algorithm for function approximation , 1994, IEEE Trans. Neural Networks.

[37]  William J. J. Rey,et al.  Robust statistical methods , 1978 .

[38]  Frank Klawonn,et al.  Computational Intelligence , 2013, Texts in Computer Science.