Deep learning classifier based on nefprox neural network

Authors

  • O. I. Chumachenko National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

DOI:

https://doi.org/10.18372/1990-5548.50.11389

Keywords:

Fuzzy classifiers, deep learning, NEFPROX neural network Restricted Boltzman Machine

Abstract

It is proposed a new class of fuzzy classifiers. It is a deep learning classifier based onNEFPROX neural network. The pre-learning is supplied with help of Restricted Boltzman Machine

Author Biography

O. I. Chumachenko, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

Candidate of Science (Engineering). Associate Professor. Technical Cybernetic Department

References

D. Nauck, U. Nauck, and R. Kruse, “Generating classification rules with the neurofuzzy system NEFCLASS.” Biennial Conference of the North American, Fuzzy Information Processing Society, 1996, pp. 466–470.

Y. Bengio, “Learning deep architectures for AI.” Foundations and trends® in Machine Learning, 2(1), pp. 1–127, 2009.

Y. Bengio, Deep learning of representations: Looking forward, Statistical Language and Speech Processing. Springer Berlin Heidelberg, 2013, pp. 1–37.

J. Schmidhuber, “Deep learning in neural networks: An overview.” Neural Networks, 61, pp. 85–117. 2015.

L. A. Zadeh, "Fuzzy algorithms." Information and Control. 12 (2), pp. 94–102, 1968.

G. Hinton, A Practical Guide to Training Restricted Boltzmann Machines, 2010, pp. 3–17.

A. Fischer, and C. Igel, An Introduction to Restricted Boltzmann Machines, 2011, pp. 1–23.

M. Nielsen, (viewed on September 20, 2016). Using neural nets to recognize handwritten digits [Electronic resourse] – Electronic data.– Mode of access: http://neuralnetworksanddeeplearning.com/chap1.html

О. I. Chumachenko. Deep Learning Classifier Based on NEFCLASS Neural Network // Electronics and Control Systems, N 3(49) – Kyiv: NAU, 2016. – pp. 79–83.

Downloads

Issue

Vol. 4 No. 50 (2016)

Section

COMPUTER-AIDED DESIGN SYSTEMS

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).