DocumentCode :
3279339
Title :
CMOS analog neural network systems based on oscillatory neurons
Author :
Linares-Barranco, B. ; Sánchez-Sinencio, E. ; Rodriguez-Vazquez, Angel ; Huertas, J.L.
Author_Institution :
Centro Nacional de Microelectron., Sevilla, Spain
Volume :
5
fYear :
1992
fDate :
10-13 May 1992
Firstpage :
2236
Abstract :
The authors discuss the design of two neural network systems based on the use of pulsing neurons. Each neuron was built as a simple voltage controlled oscillator (VCO) whose control voltage made the circuit oscillate or not oscillate. The interconnecting synapses between neurons are made with programmable transconductance amplifiers. The weight of each synapse is represented by the transconductance gain of the amplifiers, and is externally adjustable for each synapse. The oscillatory neuron circuit and the interconnection strategy for oscillatory neurons are described. Using this technique a 5-neuron Hopfield network and 6-neuron bidirectional associated memory (BAM) network were built and tested, using standard 2-μm double-metal, double polysilicon CMOS (MOSIS) chips
Keywords :
CMOS integrated circuits; analogue processing circuits; neural nets; 2 micron; CMOS analog neural network systems; Hopfield network; MOSIS; VCO; bidirectional associated memory; double polysilicon CMOS; double-metal; interconnecting synapses; oscillatory neurons; programmable transconductance amplifiers; pulsing neurons; transconductance gain; voltage controlled oscillator; Biological neural networks; Biomembranes; Cells (biology); Integrated circuit interconnections; Magnesium compounds; Neural network hardware; Neural networks; Neurons; Transconductance; Voltage-controlled oscillators;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
Type :
conf
DOI :
10.1109/ISCAS.1992.230515
Filename :
230515
Link To Document :
بازگشت