DocumentCode :
3543694
Title :
RRAM-based synapse for neuromorphic system with pattern recognition function
Author :
Park, Soojin ; Kim, Heonhwan ; Choo, M. ; Noh, Junyong ; Sheri, A. ; Jung, Sanghyuk ; Seo, Kazuyuki ; Park, Jongho ; Kim, Sungho ; Lee, Wei-Jen ; Shin, Jeyong ; Lee, Daewoo ; Choi, GanHo ; Woo, Jiyong ; Cha, Elizabeth ; Jang, Jin ; Park, C. ; Jeon, Moon-G
Author_Institution :
Gwangju Inst. of Sci. & Technol. (GIST), Gwangju, South Korea
fYear :
2012
fDate :
10-13 Dec. 2012
Abstract :
Feasibility of a high speed pattern recognition system using 1k-bit cross-point synaptic RRAM array and CMOS-based neuron chip has been experimentally demonstrated. Learning capability of a neuromorphic system comprising RRAM synapses and CMOS neurons has been confirmed experimentally, for the first time.
Keywords :
CMOS memory circuits; neural chips; pattern recognition; random-access storage; CMOS-based neuron chip; RRAM-based synapse; cross-point synaptic RRAM array; high speed pattern recognition system; neuromorphic system; pattern recognition function; storage capacity 1 Kbit; Arrays; CMOS integrated circuits; Neuromorphics; Neurons; Semiconductor device modeling; Testing; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electron Devices Meeting (IEDM), 2012 IEEE International
Conference_Location :
San Francisco, CA
ISSN :
0163-1918
Print_ISBN :
978-1-4673-4872-0
Electronic_ISBN :
0163-1918
Type :
conf
DOI :
10.1109/IEDM.2012.6479016
Filename :
6479016
Link To Document :
بازگشت