Inscriere cercetatori

Asociatia Ad Astra a cercetatorilor romani lanseaza BAZA DE DATE A CERCETATORILOR ROMANI DIN DIASPORA. Scopul acestei baze de date este aceea de a stimula colaborarea dintre cercetatorii romani de peste hotare dar si cu cercetatorii din Romania. Cercetatorii care doresc sa fie nominalizati in aceasta baza de date sunt rugati sa trimita un email la cristian.presura@gmail.com

Support vector machines on the space of Walsh functions and their properties

Domenii publicaţii > Ştiinţe informatice + Tipuri publicaţii > Articol în volumul unei conferinţe

Autori: A. Fazekas, C. Kotropoulos, I. Buciu and I. Pitas

Editorial: 2nd International Symposium on Image and Signal Processing and Analysis, ISPA, Pula, Croatia, p.43-48, 2001.

Rezumat:

The so-called support vector machine (SVM) is a special kind of the learning machines, whose idea was given by Vapnik. The learning capability of the support vector machines depends on the Vapnik-Chervonenkis- (VC) dimension of the kernel function of used. In this paper we are going to construct a new kernel function, which is based on Walsh functions, for support vector machines. We are proving some theoretical results about the VC-dimension of the support vector machines which are built in the space of the Walsh functions. This paper reports the first experimental results in order to access the properties of the support vector machines with Walsh kernel in face detection

Cuvinte cheie: Support Vector Machines

URL: http://poseidon.csd.auth.gr/EN/