Title :
SVM learning with fixed-point math
Author :
Anguita, Davide ; Boni, Andrea ; Ridella, Sandro
Author_Institution :
DIBE, Genoa Univ., Italy
Abstract :
We present in this paper an algorithm for Support Vector Machine (SVM) learning, which can be implemented using fixed-point math. The advantages of the fixed-point representation, respect to the more common floating-point one, allows us to address digital VLSI implementations of SVM. In particular, simple algorithms and simple architectures can be exploited for targeting programmable devices like Field Programmable Gate Arrays (FPGAs), which are the basis of many embedded systems. This paper focuses on the SVM learning algorithm: for the complete version of this work, including an actual FPGA realization.
Keywords :
VLSI; embedded systems; field programmable gate arrays; fixed point arithmetic; learning (artificial intelligence); support vector machines; FPGA; SVM learning algorithm; digital VLSI implementation; embedded systems; field programmable gate arrays; fixed point math; floating point math; programmable device; support vector machines; very large scale integration; Digital systems; Embedded system; Field programmable gate arrays; Hardware; Machine learning; Microelectronics; Support vector machine classification; Support vector machines; System-on-a-chip; Very large scale integration;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223727