Abstract
Fuzzy logic inspires from the non-deterministic behaviour of human brain computations. The fusion of neural networks and fuzzy logic such as neuro-fuzzy architectures is natural, as both represent elementary inspiration from brain computations involving learning, adaptation and ability to tolerate noise. This chapter focuses on neuro-fuzzy and alike solutions for machine learning from perspective of functionality, architectures and applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Pandiyan M, Mani G (2015) Embedded low power analog CMOS fuzzy logic controller chip for industrial applications. In: 2015 IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), pp 43–48
Juang C, Chen C (2014) An interval type-2 neural fuzzy chip with on-chip incremental learning ability for time-varying data sequence prediction and system control. IEEE Trans Neural Netw Learn Syst 25(1):216–228
Juang C, Juang K (2017) Circuit implementation of data-driven TSK-type interval type-2 neural fuzzy system with online parameter tuning ability. IEEE Trans Ind Electron 64(5):4266–4275
Oh J, Lee S, Yoo H (2013) 1.2-mW online learning mixed-mode intelligent inference engine for low-power real-time object recognition processor. IEEE Trans Very Large Scale Integr (VLSI) Syst 21(5):921–933
Merrikh-Bayat F, Merrikh-Bayat F, Shouraki SB (2014) The neurofuzzy computing system with the capacity of implementation on a memristor crossbar and optimization-free hardware training. IEEE Trans Fuzzy Syst 22(5):1272–1287
Yaghmourali YV, Fathi A, Hassanzadazar M, Khoei A, Hadidi K (2018) A low-power, fully programmable membership function generator using both transconductance and current modes. Fuzzy Sets Syst 337:128–142
Abolhasani A, Tohidi M, Mousazadeh M, Khoei A, Hadidi K (2013) A high speed and fully tunable MFG with new programmable CMOS OTA and new MIN circuit. In: Proceedings of the 20th International Conference Mixed Design of Integrated Circuits and Systems - MIXDES 2013, pp 169–173
Ghasemizadeh H, Fathi A, Ahmadi A (2012) Programmable fuzzifier circuits with high precision for analog neuro-fuzzy system. In: 20th Iranian Conference on Electrical Engineering (ICEE2012), pp 12–16
Afrakoti IEP, Shouraki SB, Bayat FM, Gholami M (2017) Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm. Fuzzy Sets Syst 307:115–128
Jang JR (1993) Anfis: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685
Bonanno D, Nock K, Smith L, Elmore P, Petry F (2017) An approach to explainable deep learning using fuzzy inference. In: Next-Generation Analyst V, vol 10207, p 102070D. International Society for Optics and Photonics
Deng Y, Ren Z, Kong Y, Bao F, Dai Q (2017) A Hierarchical fused fuzzy deep neural network for data classification. IEEE Trans Fuzzy Syst 25(4):1006–1012
Afrakoti IEP, Shouraki SB, Bayat FM, Gholami M (2016) Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm. Fuzzy Sets Syst 307:115–128
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Chapter Highlights
Chapter Highlights
-
The fuzziness of the NFS allows for a more relaxed input data processing.
-
There are multiple functions that can be used as MFs.
-
Deep learning architectures could be integrated with fuzzy sets and logic in order to introduce automated optimization of neural architectures.
-
ANFIS is one of the most popular NF architectures
-
FNNs separately use fuzzy and neural elements within one architecture
-
Fuzzy trees allow more complex, but compact representation of neuro-fuzzy rule base.
-
There are neural architectures that use some of the fuzzy elements, such as RBFNs and fuzzy ARTAMAP.
-
Dedicated analog hardware allows efficient implementation of NF algorithms.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Dorzhigulov, A., James, A.P. (2020). Deep Neuro-Fuzzy Architectures. In: James, A. (eds) Deep Learning Classifiers with Memristive Networks. Modeling and Optimization in Science and Technologies, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-030-14524-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-14524-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14522-4
Online ISBN: 978-3-030-14524-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)