DocumentCode :
303312
Title :
A programmable Gaussian node
Author :
Kuppuswamy, Ravishankar ; Theogarajan, Luiz ; Akers, L.A.
Author_Institution :
Center for Solid State Electron. Res., Arizona State Univ., Tempe, AZ, USA
Volume :
2
fYear :
1996
fDate :
3-6 Jun 1996
Firstpage :
880
Abstract :
An analog Gaussian basis circuit integrated with a nonvolatile storage memory cell is described. Hardware implementations of the Gaussian basis circuit with on-chip learning is needed for real time and portable applications. Each Gaussian basis cell is symbiotically inter-linked with its own long-term storage memory cell forming a highly localized architecture. Experimental results of both the Gaussian basis circuit and the memory element are presented. We show simulated results of an application of our cell in a MERAM system
Keywords :
MOS analogue integrated circuits; analogue processing circuits; analogue storage; content-addressable storage; neural chips; MERAM system; analog Gaussian basis circuit; highly localized architecture; long-term storage memory cell; multivalued exponential recurrent associative memory; nonvolatile storage memory cell; on-chip learning; portable applications; programmable Gaussian node; real-time applications; Biological system modeling; Brain modeling; Circuit simulation; Hardware; Lakes; MOSFETs; Nonvolatile memory; Solid state circuits; Symbiosis; Threshold voltage;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
Type :
conf
DOI :
10.1109/ICNN.1996.549013
Filename :
549013
Link To Document :
بازگشت