Title :
A Real-Time Learning Processor Based on K-means Algorithm with Automatic Seeds Generation
Author :
Shikano, Hirotsugu ; Ito, Kiyoto ; Fujita, Kazuhide ; Shibata, Tadashi
Author_Institution :
Univ. of Tokyo, Tokyo
Abstract :
A full-custom learning processor architecture has been developed based on the K-means algorithm aiming at realtime clustering applications. In order to accelerate the convergence and improve the quality of solutions, an automatic initial seeds generation function has been implemented in the architecture. The concept has been verified by the measurement of the proof-of-concept chip designed and fabricated in a 0.18-mum 5-metal CMOS technology. A full custom chip was also designed using the same technology and sent to fabrication and its operation was confirmed by simulation.
Keywords :
CMOS integrated circuits; learning by example; pattern clustering; real-time systems; system-on-chip; K-means algorithm; automatic initial seed generation function; automatic seed generation; convergence; full-custom learning processor architecture; metal CMOS technology; proof-of-concept chip; real-time learning processor; Acceleration; Application software; CMOS technology; Clustering algorithms; Field programmable gate arrays; Gravity; Hardware; Machine learning algorithms; Nearest neighbor searches; Partitioning algorithms;
Conference_Titel :
System-on-Chip, 2007 International Symposium on
Conference_Location :
Tampere
Print_ISBN :
978-1-4244-1368-3
Electronic_ISBN :
07EX1846C
DOI :
10.1109/ISSOC.2007.4427431
