Electronic Implementation of a Fuzzy Neuron Model With a Gupta Integrator

 

A. Ramírez–Mendoza*¹, J. L. Pérez–Silva², F. Lara–Rosano³

 

¹ Posgrado en Ingeniería, Universidad Nacional Autónoma de México *E–mail: ARamirezM@iingen.unam.mx

^2,3 Centro de Ciencias Aplicadas y Desarrollo Tecnológico Universidad Nacional Autónoma de México.

 

ABSTRACT

In this paper the electronic circuit implementation of a fuzzy neuron model with a fuzzy Gupta integrator is presented. This neuron model simulates the performance and the fuzzy response of a fast–spiking biological neuron. The fuzzy neuron response is analyzed for two classical (non–fuzzy) input signals, the results are spike trains with relative and absolute refractory period and an axonal delay. A comparison between the response of the proposed fuzzy neuron model and the intracellular registers of biological fast–spiking cortical interneurons is made, as well as the transients presented at the beginning of each spike train. Also the results obtained from the electronic circuit of the fuzzy neuron model with the Matlab^TM simulation of the mathematical model are compared.

Keywords: Artificial neurons, electronic models of neurons, axonal delay, refractory period, fast spiking neuron response, biological based neuron models, interneurons.

 

RESUMEN

En este trabajo realizamos la implantación del circuito electrónico del modelo de una neurona con un integrador difuso tipo Gupta que simula el funcionamiento y obtiene una respuesta difusa de una neurona de espigueo rápido; se dan las ecuaciones del modelo de neurona difusa y se obtiene una respuesta difusa de la neurona para dos señales de entrada no difusas. El resultado son trenes de espigas en donde se pueden apreciar el periodo refractario relativo y absoluto, así como el retardo axónico. Se compara la respuesta del modelo de neurona difusa propuesto con registros intracelulares de interneuronas corticales de espigueo rápido biológicas, así como del transitorio que presentan al inicio de cada tren de espigas. También se comparan los resultados obtenidos del circuito electrónico del modelo de neurona difusa con la simulación del modelo matemático de la neurona difusa en Matlab^TM.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

[1] A. N. Burkitt, "A review of the integrate–and–fire neuron model: I. Homogeneous synaptic input", Biological Cybernetics, Vol. 95, 2006, pp. 1–19.         [ Links ]

[2] Teresa B. Ludermir and Wilson R. de Oliveira, "Weightless Neural Models", Computer Standards & Interfaces 16, 1994, pp. 253–263.         [ Links ]

[3] Chaturvedi D.K., Satsangi P.S. and Prem K. Kalra, "New Neuron Models for Simulating Rotating Electrical Machines and load forecasting problems", Electric Power Systems Research 52, 1999, pp.123–131.         [ Links ]

[4] Pérez S. J.L., Herrera A., et al, "Electronics Implementation of a Neuron Model with parabolic burst response", Third International Workshop on Design of Mixed–Mode Integrated Circuits and Applications, 26–28 July 1999, pp. 122–125.         [ Links ]

[5] Pérez S. J. L., Garces A., et al, "Electronic Model of a Neuronal Sinapsis of Voltage to Frequency, and Frequency to Voltage conversion", Third International Workshop on Design of Mixed–Mode Integrated Circuits and Applications, 26–28 July 1999, pp.171–174.         [ Links ]

[6] Ramírez Mendoza Abigaíl M. E., "Modelado Electrónico de dos Neuronas Integradoras Borrosas", Tesis de Maestría, División de Estudios de Posgrado de la Facultad de Ingeniería de la U.N.A.M., México, 1998.         [ Links ]

[7] Pérez J. L., Ramírez A., "Two New Models of Integrative Fuzzy Neuron", Instrumentation & Development, Vol. 5, Nr.3, Diciembre, 2001, pp. 140–145.         [ Links ]

[8] Pérez S. J. L., Lara–Rosano F., Herrera, A. et al, "Electronic Model of a Extended Fuzzy Neuron", Proceedings of The Second Join México – E.U.A. International Conference on Neural Networks and Neurocontrol (Sian Ka'an 97), Playa del Carmen, México, Agosto 19–29, 1997, pp. 189–199.         [ Links ]

[9] Gupta M.M. and Qi J., "On Fuzzy Neuron Models",         [ Links ] Fuzzy logic for the management of uncertainty, Ed. Lotfi A. Zadeh and Janusz Kacprzyk, ISBN: 0–471–54799–9, 1992, pp. 479–491.         [ Links ]

[10] N. D. Velasco, R. Ávila–Pozos, F. R. Godínez, "Desarrollo de un software de estimulación y adquisición de señales eléctricas celulares, basado en una tarjeta comercial de adquisición de datos", Revista mexicana de ingeniería biomédica Vol. XXVI, No. 2, Septiembre, 2005, pp. 92–105.         [ Links ]

[11] Nicolas Langlois, Pierre Miché, Abdelaziz Bensrhair, "Analogue circuits of a learning spiking neuron model", IEEE, 2000, pp. 485–489.         [ Links ]

[12] Jayawa H. B. Wijekoon and Piotr Dudek, "Integrated circuit implementation of a cortical neuron", IEEE, 2008, pp. 1784–1787.         [ Links ]

[13] Eugene M. Izhikevich, "Simple Model of Spiking Neurons", IEEE Transactions on neural networks, Vol. 14, No. 6, November, 2003, pp. 1569–1572.         [ Links ]

[14] Witold Pedrycz, Marek Reformat, and Kuwen Li, "OR/AND Neurons and the development of interpretable logic models", IEEE Transactions on neural networks, Vol. 17, No. 3, May, 2006, pp. 636–658.         [ Links ]

[15] Gerstner Wulfram, Werner Kistler, "Spiking Neuron Models", Ed. Cambridge University Press, 2002, pp. 1–10, 93–94.         [ Links ]

[16] J.L. Pérez S., A. Garcés M., F. Cabiedes C., A. Miranda V., "Electronic model of a dubois fuzzy integration neuron", Journal of Applied Research and Technology, Vol.7 No. 1 April 2009, pp. 73–82.         [ Links ]

[17] M. Sekerli, R. J. Butera, "An Implementation of a Simple Neuron Model in Field Programmable Analog Arrays", Proceedings of the 26th Annual International Conference of the IEEE EMBS, San Francisco, CA, USA, September 1–5, 2004, pp. 4564–4567.         [ Links ]

[18] David Golomb, Karnit Donner, Liron Shacham, Dan Shlosberg, Yael Amitai, David Hansel, "Mechanisms of Firing Patterns in Fast–Spiking Cortical Interneurons", PLoS Computational Biology, Vol. 3 No. 8, agosto 2007, pp. 1498–1512.         [ Links ]

[19] Evyatar Av–Ron, Hanna Parnas, Lee A. Segel, "A basic biophysical model for bursting neurons", Biological Cybernetics, Springer–Verlag, 1993, Vol. 69, pp. 87–95.         [ Links ]

[20] M. Scholles, B.J. Hosticka, M. Kesper, P. Richert, and M. Schwarz, "Biologically–Inspired Artificial Neurons: Modeling and Applications", Proceedings of 1993 International Joint Conference on Neural Networks, 1993, pp. 2300–2303.         [ Links ]

[21] Ramírez A., Pérez J. L., "A Fuzzy Gupta Integrator Neuron Model with Spikes Response and Axonal delay", in Advances in Artificial Intelligence & Engineering Cybernetics, Vol. IX George E. Lasker (Ed.), Windsor, Canada: IIAS, ISBN: 1894613449, 2002, pp.12 – 16.         [ Links ]

[22] Lazzaro J., "Low Power Silicon Spiking Neurons and Axons", Circuits and Systems, ISCAS'92 Proceedings, IEEE International Symposium, Vol. 5, San Diego, CA, USA, 10–13 May 1992, pp. 2220–2223.         [ Links ]

[23] Inawashiro S., Miyake S., Ito M., "Spiking Neuron Models for Regular–Spiking, Intrinsically Bursting, and Fast–Spiking Neurons", Proceedings 6th International Conference on Neural Information Processing, Vol. 1, 16-20 November 1999, pp. 32–36.         [ Links ]

[24] Daniel J. Amit, Modeling Brain Function, Cambridge University Press, New York, United States of America, 1989, pp. 12–17, 375–377.         [ Links ]

[25] Gordon M. Shepherd, "Neurobiology", Oxford University Press, New York, United States of America, 1994, pp. 54, 88–89.         [ Links ]

[26] www.altera.com        [ Links ]