Title :
Analog VLSI current mode implementation of artificial neural networks
Author :
El-Masry, Ezz I. ; Maundy, Brent J. ; Yang, Hong-kui
Author_Institution :
Dept. of Electr. Eng., Tech. Univ. Nova Scotia, Halifax, NS, Canada
Abstract :
In this paper we examine all current-mode building blocks for implementation of artificial neural networks. The building blocks proposed include a current dependent pulse generator, a pulse frequency modulator used to multiply incoming pulses with variable weights, and a current in/current out sigmoid function circuit. The circuits can be easily implemented in a standard CMOS VLSI process. Simulations are presented to confirm the validity of the proposed circuits
Keywords :
CMOS analogue integrated circuits; VLSI; analogue computer circuits; analogue multipliers; circuit analysis computing; neural chips; pulse generators; CMOS VLSI process; analog VLSI circuit; artificial neural networks; current dependent pulse generator; current-mode building blocks; pulse frequency modulator; pulse multiplication; sigmoid function circuit; simulations; Artificial neural networks; Capacitors; Frequency; Pulse amplifiers; Pulse circuits; Pulse generation; Pulse modulation; Transconductance; Very large scale integration; Voltage;
Conference_Titel :
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-1760-2
DOI :
10.1109/MWSCAS.1993.343332
