Title :
Analog circuit for synapse neural networks VLSI implementation
Author_Institution :
Lebanese Univ., Beirut, Lebanon
Abstract :
In this paper the author presents an analog VLSI circuit to implement the synapse operation in artificial neural network systems. This circuit is a two-quadrant (or four-quadrant) analog multiplier. The output of the synapse circuit is in current and it is proportional to the multiplication of two input voltages: the weight voltage and the pattern information input voltage (or the output voltage of the neuron). The main feature of the multiplier is the high value of the weight voltage range, which varies between the ground voltage and the supply voltage [0:Vdd]
Keywords :
CMOS analogue integrated circuits; VLSI; analogue processing circuits; neural chips; 0.5 micron; Mietec CMOS technology; VLSI implementation; analog VLSI circuit; artificial neural network systems; four-quadrant analog multiplier; pattern information input voltage; synapse neural networks; two-quadrant analog multiplier; weight voltage; Analog circuits; Capacitors; Cities and towns; Equations; Neural networks; Neurons; Resistors; Threshold voltage; Transconductance; Very large scale integration;
Conference_Titel :
Electronics, Circuits and Systems, 2000. ICECS 2000. The 7th IEEE International Conference on
Conference_Location :
Jounieh
Print_ISBN :
0-7803-6542-9
DOI :
10.1109/ICECS.2000.913045
