DocumentCode
1817986
Title
LSI implementation of pulse-output neural network with programmable synapse
Author
Sato, Shigeo ; Yumine, Manabu ; Yama, Takayuki ; Murota, Junichi ; Nakajima, Koji ; Sawada, Yasuji
Author_Institution
Res. Inst. of Electr. Commun., Tohoku Univ., Sendai, Japan
Volume
1
fYear
1992
fDate
7-11 Jun 1992
Firstpage
172
Abstract
A microchip of a neural circuit with pulse representation has been fabricated. The neuron output is a voltage pulse train. The synapse is a constant current source whose output is proportional to the duty ratio of neuron output. Membrane potential is charged by collection of synaptic currents through an RC circuit, providing analog operation similar to the biological neural system. A 4-b SRAM (static random-access memory) was used as the memory of a synaptic weight. The measured I/O characteristics of the neurons and the synapses were as expected. The ability of the network operation was demonstrated by assigning the synaptic weights as an A/D converter
Keywords
SRAM chips; large scale integration; neural chips; 4 bit; A/D converter; LSI; RC circuit; SRAM; analog operation; constant current source; duty ratio; membrane potential; neural circuit microchip; neuron output; programmable synapse; pulse representation; pulse-output neural network; static random-access memory; synaptic currents; synaptic weight; voltage pulse train; Biological neural networks; Biomembranes; Circuit noise; Large scale integration; Neural network hardware; Neural networks; Neurons; Pulse circuits; Random access memory; Voltage;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location
Baltimore, MD
Print_ISBN
0-7803-0559-0
Type
conf
DOI
10.1109/IJCNN.1992.287140
Filename
287140
Link To Document