Title :
Hardware-based support vector machine classification in logarithmic number systems
Author :
Khan, Faisal M. ; Arnold, Mark G. ; Pottenger, William M.
Author_Institution :
Dept. of Comput. Sci. & Eng., Lehigh Univ., Bethlehem, PA, USA
Abstract :
Support vector machines are emerging as a powerful machine-learning tool. Logarithmic number systems (LNS) utilize the property of logarithmic compression for numerical operations. We present an implementation of a digital support vector machine (SVM) classifier using LNS in which, when compared with other implementations, considerable hardware savings are achieved with no significant loss in classification accuracy.
Keywords :
data compression; learning (artificial intelligence); pattern classification; support vector machines; LNS; classification accuracy; digital SVM classifier; hardware savings; hardware-based support vector machine classification; logarithmic compression; logarithmic number systems; machine-learning tool; numerical operations; Application software; Computer science; Event detection; Hardware; Kernel; Machine learning; Neural networks; Power engineering and energy; Support vector machine classification; Support vector machines;
Conference_Titel :
Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on
Print_ISBN :
0-7803-8834-8
DOI :
10.1109/ISCAS.2005.1465795
