Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Cost-conscious multiple kernel learning Mehmet Gnen *, Ethem Alpaydin

Summary: Cost-conscious multiple kernel learning
Mehmet Gönen *, Ethem Alpaydin
Department of Computer Engineering, Bogaziçi University, TR-34342 Bebek, _Istanbul, Turkey
a r t i c l e i n f o
Article history:
Received 30 April 2009
Received in revised form 1 November 2009
Available online 4 January 2010
Communicated by Y. Ma
Support vector machines
Kernel combination
Multiple kernel learning
a b s t r a c t
Recently, it has been proposed to combine multiple kernels using a weighted linear sum. In certain appli-
cations, different kernels may be using different input representations and these methods do not consider
neither the cost of acquiring them nor the cost of evaluating the kernels. We generalize the framework of
MULTIPLE KERNEL LEARNING (MKL) for this cost-conscious methodology. On 12 benchmark data sets from the
UCI repository, we compare MKL and its cost-conscious variants in terms of accuracy, support vector
count, and total cost. Cost-conscious MKL achieves statistically similar accuracy results by using fewer


Source: Alpaydın, Ethem - Department of Computer Engineering, Bogaziçi University


Collections: Computer Technologies and Information Sciences