Title :
A Beta neuron in CMOS subthreshold mode
Author :
Samet, Mounir ; Masmoudi, Mohamed ; Ghozzi, Fahmi ; Ben Ayed, Yassine ; Alimi, Adel M.
Author_Institution :
Dept. of Electr. Eng., Nat. Sch. of Eng., Sfax, Tunisia
fDate :
6/20/1905 12:00:00 AM
Abstract :
Beta Basis Function Neural Networks (BBFNN) are powerful systems for learning and universal approximation characteristics. In this paper, we present a hardware implementation of the Beta neuron using the CMOS subthreshold-mode. We describe a low power low voltage analog Beta neuron circuit. Three main modules are used to realize the Beta function: a logarithmic current to voltage converter, a multiplier and an exponential voltage to current converter. Simulation results prove the validity of our neural hardware implementation. The control parameters of the Beta function are independent and are made easily by current sources. This analog implementation can be used easily to realize analog BBFNN
Keywords :
CMOS analogue integrated circuits; SPICE; analogue processing circuits; circuit simulation; low-power electronics; neural chips; radial basis function networks; Beta function control parameters; Beta neuron; CMOS subthreshold mode; SPICE simulation results; analog implementation; beta basis function neural networks; current sources; exponential voltage to current converter; hardware implementation; learning; logarithmic current to voltage converter; low power low voltage analog Beta neuron circuit; multiplier; universal approximation characteristics; Artificial neural networks; CMOS technology; Circuits; Hardware; Low voltage; MOSFETs; Neural networks; Neurons; Shape; Very large scale integration;
Conference_Titel :
Microelectronics, 1998. ICM '98. Proceedings of the Tenth International Conference on
Conference_Location :
Monastir
Print_ISBN :
0-7803-4969-5
DOI :
10.1109/ICM.1998.825621
