J. L. Pérez S.*1, A. Garcés M.2, F. Cabiedes C.3, A. Miranda V.4
1,2,3,4 Centro de Ciencias Aplicadas y Desarrollo Tecnológico Universidad Nacional Autónoma de México *E–mail:pepito@aleph.cinstrum.unam.mx
ABSTRACT
In this work, we present a fuzzy electronic neuron that has a Dubois fuzzy integration method, an activation function with a fuzzy threshold, and a fuzzy response. We generated a fuzzy sum of the input signals and a shooting threshold value defined by means of a triangular or sinusoidal membership function. We present the electronic circuits, the oscilograms of the neuron responses, the value of the fuzzy integral, and we compare their behavior with those of a conventional leaky integrator neuron.
Keywords: Biological based neuron models, artificial neuron models, Fuzzy neuron models.
]]>RESUMEN
En este trabajo presentamos una neurona electrónica borrosa que contiene un integrador tipo Dubois, una función de activación con umbral borroso y respuesta borrosa. Generamos un sumador borroso de señales de entrada y un valor de disparo de umbral definido por medio de una función de membresía triangular o sinusoidal. Presentamos los circuitos electrónicos, los oscilogramas de la respuesta de la neurona, el valor de la integral borrosa, y comparamos estas características con una neurona integradora con fugas convencional.
DESCARGAR ARTÍCULO EN FORMATO PDF
References
[1] Mc Culloch W.S., Pitts W.A. "A logical calculus of the ideas imminent in nervous activity". Bull. Math. Biophys., 5 (1943). [ Links ]
[2] Pozin N.V. Lyubinskii, I A, Neuron Model. Report Number FTD–HT–66–103 9 September 1966. 5 pages. [ Links ]
[3] J.A. Deutsch. An electrophysiological stimulator with digital logic. J. exp. analysis Behav. 9 (1966). pp. 399–400. [ Links ]
[4] Mitchell RA et al., J Appl Physiol 18. 523–533. (1963). [ Links ]
[5] Hormann, "Gaku: An Artificial Student." Behavioral Science. vol. 10. No. 1 (January. 1965). pp. 88–107. [ Links ]
[6] Frank Rosenblatt. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. Psychological Review. vol. 65. No. 6. pp. 386-408. November. (1958). [ Links ]
[7] Caianiello, F.R. Outline of a theory of thought–processes and thinking machines J. Theoret. Binl. 1. 204–235 (1961). [ Links ]
[8] B. Widrow and M.F. Hoff, Associative Storage and Retrieval of Digital Information in networks of Adaptive Neurons. Biological Prototypes and Synthetic Systems. 1:160. (1962). [ Links ]
[9] Lewis F.R. Structural correlates of function in the anuran amphibian papilla. Scanning Flectron Microsc 2. pag 429–436. (1977). [ Links ]
[10] French A.S., Stein R.B. "Flexible Neural Analog using integrated circuits". IEEE Trans. Binmed. Fng. 17. 248–253 (1970). [ Links ]
[11] Mitchell. P. Molecule, group and electron translocation through natural membranes. Biochem Snc. Symp. 22 pag 142–168. (1981). [ Links ]
[12] Vittoz. F.A. "Analog VLSI Signal Processing: Why. Where and How?" Journal of VLSI Signal Processing. 8 & Analog Integrated Circuits and Signal Processing. 2744. (1994). [ Links ]
[13] Alexandre R.S. Romariz, Kelvin Wagner Optoelectronic Implementation of a FitzHugh–Nagumo Neural Model. IEEE Journal of Solid–State Circuits. 26 (7): 956–965. (1991). [ Links ]
[14] R.D. Pinto, P. Varona, A.R. Volkovskii. A. Szucs, H.D. Abarbanel, and M.I. Rabinovich. Synchronous behavior of two coupled electronic neurons. Phys Rev F. vol. 62. pp. 2644–56. (2000). [ Links ]
[15] Y.J. Lee, Lee, J., Kim, Y.B., Ayers J., Volkovskii. A., Selverston. A., Abarbanel, H., Rabinovich. M., "Low Power Real Time Flectronic Neuron VLSI Design Using Subthreshnld Techniques. IEEE Circuits and Systems. vol. 4. pp. 744–747. (2004). [ Links ]
[16] Shin'Ichiro Kanoh. Makoto Imai. Nozomu Hoshimiy. Analog LSI Neuron Model inspired by biological excitable membrane. Systems and Computers in Japan, Volume 36 Issue 6. Pages 84 – 91. (2005). [ Links ]
[17] A.van Schaik, Building blocks for electronic spiking neural networks. Volume 14. Issues 6–7, Pages 617–6289 (2001). [ Links ]
[18] Szlavik Robert B.; Bhuiyan Abuhanif K.; Carver Anthony; Jenkins Frank. Neural–electronic inhibition simulated with a Neuron Model implemented in SPICE. IEEE Engineering in Medicine and Biology. vol. 14. n 1. pp. 109–115. (2006). [ Links ]
[19] A. Volkovskii, S. Bruginni, R. Levi, M. Rabinovich, A. Selverston and H.D.I. Abarbanel. Analog electronic Model of the lobster pyloric central pattern generator. Journal of Physics: Conference Series 23 47–57 (2005). [ Links ]
[20] Wu J, DiCecco J, Sun Y, Hill R. An analog Neuron emulator for education and testing of neurophysiological instruments. Society for Neuroscience 34th Annual Meeting. San Diego. CA. October 23–27. (2004). [ Links ]
[21] Breau F. Main–Cannon S. Davis R. Wu J. DiCecco J. Sun Y. The Neuron emulator: an undergraduate biomedical engineering design project. 31 Northeast Bioengineering Conference. Hoboken. NJ. April 2–3. (2005). [ Links ]
[22] Allen I. Selverston, Mikhail I. Rabinovich, Henry D. Abarbanel, Robert Elson, Attila Szucs, Reynaldo D. Pinto, Ramon Huerta, Pablo Varona. Reliable circuits from irregular Neurons: A dynamical approach to understanding central pattern generators. Journal of Physiology–Paris. vol. 94. No. 5–6., pp. 357–374 (2000). [ Links ]
[23] Maeda Ynshinnbu Satn. Shunsuke Makinn Hiden. Bifurcation Structure of an Electronic Circuit Model for Neuronal Firings. Transactions of the Institute of Electrical Engineers of Japan. C. ISSN:0385–4221, Vol. 121–C; No.7; 1153–1159 (2001). [ Links ]
[24] Shinya Suenaga. Yoshihiro Hayakawa and Koji Nakajima. Design of a Neural network Chip for the Burst ID Model with Ability of Burst Firing. IEICE Transactions on Fundamentals of Electronics. Communications and Computer Sciences F90–A(4):715–723 (2007) [ Links ]
[25] Perez S. J.L., Calva G.: Modelo electrónico de un sistema Neuronal. Memorias del IV Simposio Nacional de Instrumentación. México. 1987. [ Links ]
[26] Perez S. J.L.: Diseño de un modelo de Neurona analógico. Reporte técnico. Centro de Instrumentos UNAM. (1974). Mexico. 10 pag. [ Links ]
[27] Zadeh L.A.: Fuzzy sets. Inform Control. (1965). 338–353. [ Links ]
]]>[28] Wee W.C., Fu K.S. "A formulation of Fuzzy Automata and its applications as a Model of Learning system". IEEE Trans. Syst. Sci. Cybernetics. (1969). SSC–5. [ Links ]
[29] Lee., F.T. Lee. Fuzzy sets and neural networks. J. Cybernetics. (1974). 4. 83–103. [ Links ]
[30] Keller., D. Hunt. Incorporating fuzzy membership functions into the perceptron algorithm. IEEE Trans. Pattern Anal. Machine Intelligence. (1985). 7. 693–699. [ Links ]
[31] Yamakawa y S. Tnmnda. A fuzzy Neuron and its application to pattern recognition. Proc. Third IFSA Congr., Seattle. August 6–11. 30–38, 1989. [ Links ]
[32] Requema y M. Delgado. "A Model of fuzzy Neuron". Proc. 2nd. Int. Cnnf. Fuzzy logic Neural networks. (IIZUKA'90). Iizuka. Japón. July 20–24. 13–26 (1990). [ Links ]
]]>[33] Kandel A. Fuzzy Switching and automata. Crane, Russak & Company. New York. (1979). [ Links ]
[34] Dubnis D. Towars Fuzzy Differential Calculus. Fuzzy Sets and Systems., 8. 1–17 (1982). [ Links ]
]]>