TY - GEN
T1 - Simple power series for pattern classification
AU - Toh, Kar Ann
PY - 2007
Y1 - 2007
N2 - We show in this paper, that a simple power series model with appropriate learning formulation, can be used for effective pattern classification. Essentially, an error counting cost function is adopted. Through a linear parametric power series model and a quadratic approximation to the error cost, a deterministic solution is derived. This solution is seen to relate to a class-specific setting of the more generic weighted least-squares. A tuning mechanism is thus incorporated for robust applications. Our empirical evaluations show effectiveness of the classifier.
AB - We show in this paper, that a simple power series model with appropriate learning formulation, can be used for effective pattern classification. Essentially, an error counting cost function is adopted. Through a linear parametric power series model and a quadratic approximation to the error cost, a deterministic solution is derived. This solution is seen to relate to a class-specific setting of the more generic weighted least-squares. A tuning mechanism is thus incorporated for robust applications. Our empirical evaluations show effectiveness of the classifier.
UR - http://www.scopus.com/inward/record.url?scp=35248812568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=35248812568&partnerID=8YFLogxK
U2 - 10.1109/ICIEA.2007.4318486
DO - 10.1109/ICIEA.2007.4318486
M3 - Conference contribution
AN - SCOPUS:35248812568
SN - 1424407370
SN - 9781424407378
T3 - ICIEA 2007: 2007 Second IEEE Conference on Industrial Electronics and Applications
SP - 641
EP - 646
BT - ICIEA 2007
T2 - 2007 2nd IEEE Conference on Industrial Electronics and Applications, ICIEA 2007
Y2 - 23 May 2007 through 25 May 2007
ER -