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

fYear

2007

fDate

20-21 Nov. 2007

Firstpage

1

Lastpage

4

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;

fLanguage

English

Publisher

ieee

Conference_Titel

System-on-Chip, 2007 International Symposium on

Conference_Location

Tampere

ISSN

07EX1846C

Print_ISBN

978-1-4244-1368-3

Electronic_ISBN

07EX1846C

Type

conf

DOI

10.1109/ISSOC.2007.4427431

Filename

4427431