PROCEEDINGS OF THE JOINT CONFERENCE ON NEURAL NETWORKS IJCNN

dc.creatorKottow, D
dc.creatorRuiz Del Solar San Martin, Javier
dc.date2016-12-27T21:48:54Z
dc.date2022-06-17T20:33:58Z
dc.date2016-12-27T21:48:54Z
dc.date2022-06-17T20:33:58Z
dc.date.accessioned2023-08-23T00:30:50Z
dc.date.available2023-08-23T00:30:50Z
dc.identifier1990595
dc.identifierhttps://hdl.handle.net/10533/165073
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8355424
dc.descriptionThe automatic selection of feature variables is a task of increasing interest in the field of pattern recognition. Neural models have recently been used for this purpose. Among other models, the adaptive-subspace SOM (ASSOM) stands out because of its simplicity and biological plausibility. However, the main drawback of its application in image processing systems is that a priori information is necessary to choose a suitable network size and topology in advance. This article introduces the adaptive-subspace growing cell structures (ASGCS) network, which corresponds to a further improvement of the ASSOM that overcomes its main drawbacks. The ASGCS network is described and some examples of automatic generation of Gabor-like feature filter are given.
dc.descriptionFONDECYT
dc.description0
dc.descriptionFONDECYT
dc.languageeng
dc.publisherIEEE TECHNICAL COMMITTEE ON DATA ENGINEERING
dc.relationinstname: Conicyt
dc.relationreponame: Repositorio Digital RI2.0
dc.relationinstname: Conicyt
dc.relationreponame: Repositorio Digital RI 2.0
dc.relationinfo:eu-repo/grantAgreement/Fondecyt/1990595
dc.relationinfo:eu-repo/semantics/dataset/hdl.handle.net/10533/93479
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titleA NEW NEURAL NETWORK MODEL FOR AUTOMATIC GENERATION OF GABOR-LIKE FEATURE FILTERS
dc.titlePROCEEDINGS OF THE JOINT CONFERENCE ON NEURAL NETWORKS IJCNN
dc.typeCapitulo de libro
dc.typeinfo:eu-repo/semantics/bookPart


Este ítem pertenece a la siguiente institución