Mostra el registre d'ítem simple
Selection of basis functions guided by the L2 soft margin
dc.contributor.author | Barrio Moliner, Ignacio |
dc.contributor.author | Romero Merino, Enrique |
dc.contributor.author | Belanche Muñoz, Luis Antonio |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2020-04-14T08:24:13Z |
dc.date.available | 2020-04-14T08:24:13Z |
dc.date.issued | 2007 |
dc.identifier.citation | Barrio, I.; Romero, E.; Belanche, L. Selection of basis functions guided by the L2 soft margin. A: International Conference on Artificial Neural Networks. "Artificial Neural Networks, ICANN 2007, 17th International Conference: Porto, Portugal, September 9-13, 2007: proceedings, part I". Berlín: Springer, 2007, p. 421-430. |
dc.identifier.isbn | 978-3-540-74690-4 |
dc.identifier.uri | http://hdl.handle.net/2117/183259 |
dc.description.abstract | Support Vector Machines (SVMs) for classification tasks produce sparse models by maximizing the margin. Two limitations of this technique are considered in this work: firstly, the number of support vectors can be large and, secondly, the model requires the use of (Mercer) kernel functions. Recently, some works have proposed to maximize the margin while controlling the sparsity. These works also require the use of kernels. We propose a search process to select a subset of basis functions that maximize the margin without the requirement of being kernel functions. The sparsity of the model can be explicitly controlled. Experimental results show that accuracy close to SVMs can be achieved with much higher sparsity. Further, given the same level of sparsity, more powerful search strategies tend to obtain better generalization rates than simpler ones. |
dc.format.extent | 10 p. |
dc.language.iso | eng |
dc.publisher | Springer |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial |
dc.subject.lcsh | Kernel functions |
dc.subject.lcsh | Support vector machines |
dc.subject.other | Basis function |
dc.subject.other | Forward selection |
dc.subject.other | Relevance vector machine |
dc.subject.other | Radial basis function |
dc.subject.other | Sparse model |
dc.title | Selection of basis functions guided by the L2 soft margin |
dc.type | Conference report |
dc.subject.lemac | Kernel, Funcions de |
dc.contributor.group | Universitat Politècnica de Catalunya. SOCO - Soft Computing |
dc.identifier.doi | 10.1007/978-3-540-74690-4_43 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://link.springer.com/chapter/10.1007/978-3-540-74690-4_43 |
dc.rights.access | Open Access |
local.identifier.drac | 27666827 |
dc.description.version | Postprint (author's final draft) |
local.citation.author | Barrio, I.; Romero, E.; Belanche, Ll. |
local.citation.contributor | International Conference on Artificial Neural Networks |
local.citation.pubplace | Berlín |
local.citation.publicationName | Artificial Neural Networks, ICANN 2007, 17th International Conference: Porto, Portugal, September 9-13, 2007: proceedings, part I |
local.citation.startingPage | 421 |
local.citation.endingPage | 430 |