A NEW NEURAL NETWORK MODEL FOR AUTOMATIC GENERATION OF GABOR-LIKE FEATURE FILTERS
PROCEEDINGS OF THE JOINT CONFERENCE ON NEURAL NETWORKS IJCNN
dc.creator | Kottow, D | |
dc.creator | Ruiz Del Solar San Martin, Javier | |
dc.date | 2016-12-27T21:48:54Z | |
dc.date | 2022-06-17T20:33:58Z | |
dc.date | 2016-12-27T21:48:54Z | |
dc.date | 2022-06-17T20:33:58Z | |
dc.date.accessioned | 2023-08-23T00:30:50Z | |
dc.date.available | 2023-08-23T00:30:50Z | |
dc.identifier | 1990595 | |
dc.identifier | https://hdl.handle.net/10533/165073 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8355424 | |
dc.description | The 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.description | FONDECYT | |
dc.description | 0 | |
dc.description | FONDECYT | |
dc.language | eng | |
dc.publisher | IEEE TECHNICAL COMMITTEE ON DATA ENGINEERING | |
dc.relation | instname: Conicyt | |
dc.relation | reponame: Repositorio Digital RI2.0 | |
dc.relation | instname: Conicyt | |
dc.relation | reponame: Repositorio Digital RI 2.0 | |
dc.relation | info:eu-repo/grantAgreement/Fondecyt/1990595 | |
dc.relation | info:eu-repo/semantics/dataset/hdl.handle.net/10533/93479 | |
dc.rights | info:eu-repo/semantics/openAccess | |
dc.title | A NEW NEURAL NETWORK MODEL FOR AUTOMATIC GENERATION OF GABOR-LIKE FEATURE FILTERS | |
dc.title | PROCEEDINGS OF THE JOINT CONFERENCE ON NEURAL NETWORKS IJCNN | |
dc.type | Capitulo de libro | |
dc.type | info:eu-repo/semantics/bookPart |