Memristive Neuro-Fuzzy System

In this paper, a novel neuro-fuzzy computing system is proposed where its learning is based on the creation of fuzzy relations by using a new implication method without utilizing any exact mathematical techniques. Then, a simple memristor crossbar-based analog circuit is designed to implement this neuro-fuzzy system which offers very interesting properties. In addition to high connectivity between neurons and being fault tolerant, all synaptic weights in our proposed method are always non-negative, and there is no need to adjust them precisely. Finally, this structure is hierarchically expandable, and it can do fuzzy operations in real time since it is implemented through analog circuits. Simulation results confirm the efficiency and applicability of our neuro-fuzzy computing system. They also indicate that this system can be a good candidate to be used for creating artificial brain.

[1]  Bernabé Linares-Barranco,et al.  On neuromorphic spiking architectures for asynchronous STDP memristive systems , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[2]  Farnood Merrikh-Bayat,et al.  Memristor-based circuits for performing basic arithmetic operations , 2010, WCIT.

[3]  Saeed Bagheri Shouraki,et al.  A novel fuzzy approach to modeling and control and its hardware implementation based on brain functionality and specifications , 2000 .

[4]  Jacques-Olivier Klein,et al.  Hight fault tolerance in neural crossbar , 2010, 5th International Conference on Design & Technology of Integrated Systems in Nanoscale Era.

[5]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[6]  Massimiliano Versace,et al.  The brain of a new machine , 2010, IEEE Spectrum.

[7]  E. H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Man Mach. Stud..

[8]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[9]  Massimiliano Di Ventra,et al.  Memristive model of amoeba’s learning , 2008 .

[10]  Marzuki Khalid,et al.  Tuning of a neuro-fuzzy controller by genetic algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[11]  A. Ayatollahi,et al.  Implementation of biologically plausible spiking neural network models on the memristor crossbar-based CMOS/nano circuits , 2009, 2009 European Conference on Circuit Theory and Design.

[12]  D. Stewart,et al.  The crossbar latch: Logic value storage, restoration, and inversion in crossbar circuits , 2005 .

[13]  L. Chua.  Memristor-The missing circuit element , 1971 .

[14]  Nadine N. Tschichold-Gürman.  The neural network model RuleNet and its application to mobile robot navigation , 1997, Fuzzy Sets Syst..

[15]  Massimiliano Di Ventra,et al.  Practical Approach to Programmable Analog Circuits With Memristors , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[16]  Masayuki Murakami,et al.  A study on the modeling ability of the IDS method: A soft computing technique using pattern-based information processing , 2007, Int. J. Approx. Reason..

[17]  Farnood Merrikh-Bayat,et al.  Bottleneck of using single memristor as a synapse and its solution , 2010, ArXiv.

[18]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[19]  Dalibor Biolek,et al.  SPICE modeling of memristive, memcapacitative and meminductive systems , 2009, 2009 European Conference on Circuit Theory and Design.

[20]  Hamid R. Berenji,et al.  Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[21]  J. Knott.  The organization of behavior: A neuropsychological theory , 1951 .

[22]  Stoddart,et al.  Electronically configurable molecular-based logic gates , 1999, Science.

[23]  Farnood Merrikh-Bayat,et al.  Mixed analog-digital crossbar-based hardware implementation of sign–sign LMS adaptive filter , 2011 .

[24]  K. D. Cantley,et al.  Hebbian Learning in Spiking Neural Networks With Nanocrystalline Silicon TFTs and Memristive Synapses , 2011, IEEE Transactions on Nanotechnology.

[25]  Weidong Wang,et al.  Study of filter characteristics based on PWL memristor , 2009, 2009 International Conference on Communications, Circuits and Systems.

[26]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[27]  LangJérôme,et al.  Fuzzy sets in approximate reasoning, part 2 , 1991 .

[28]  Blaise Mouttet,et al.  Proposal for Memristors in Signal Processing , 2008, NanoNet.

[29]  J. Fodor.  On fuzzy implication operators , 1991 .

[30]  Leszek Rutkowski,et al.  Flexible Neuro-Fuzzy Systems: Structures, Learning and Performance Evaluation—L. Rutkowski (Boston, MA: Kluwer Academic Publishers, 2004, ISBN: 1-402-08042-5) Reviewed by A. E. Gaweda , 2006, IEEE Transactions on Neural Networks.

[31]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[32]  Fabrizio Lombardi,et al.  On the defect tolerance of nano-scale two-dimensional crossbars , 2004 .

[33]  J. Yang,et al.  Memristive switching mechanism for metal/oxide/metal nanodevices. , 2008, Nature nanotechnology.

[34]  Farnood Merrikh-Bayat,et al.  Memristor Crossbar-Based Hardware Implementation of the IDS Method , 2010, IEEE Transactions on Fuzzy Systems.

[35]  Chia-Feng Juang,et al.  A Type-2 Self-Organizing Neural Fuzzy System and Its FPGA Implementation , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[36]  J. Suehle,et al.  A Flexible Solution-Processed Memristor , 2009, IEEE Electron Device Letters.

[37]  Massimiliano Di Ventra,et al.  Memristive model of amoeba learning. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[38]  D. Dubois,et al.  Fuzzy sets in approximate reasoning: a personal view , 1996 .

[39]  Gregory S. Snider,et al.  Spike-timing-dependent learning in memristive nanodevices , 2008, 2008 IEEE International Symposium on Nanoscale Architectures.