Utiliza este identificador para citar o vincular este elemento: http://hdl.handle.net/10553/17857
Títulos: Learning to recognize faces incrementally
Autores/as: Déniz Suárez, Oscar
Lorenzo Navarro, José Javier 
Castrillón-Santana, Modesto 
Méndez Rodríguez, Juan Ángel 
Falcón Martel, Antonio 
Clasificación UNESCO: 120304 Inteligencia artificial
Fecha de publicación: 2007
Resumen: Most face recognition systems are based on some form of batch learning. Online face recognition is not only more practical, it is also much more biologically plausible. Typical batch learners aim at minimizing both training error and (a measure of) hypothesis complexity. We show that the same minimization can be done incrementally as long as some form of ”scaffolding” is applied throughout the learning process. Scaffolding means: make the system learn from samples that are neither too easy nor too difficult at each step. We note that such learning behavior is also biologically plausible. Experiments using large sequences of facial images support the theoretical claims. The proposed method compares well with other, numerical calculus-based online learners.
URI: http://hdl.handle.net/10553/17857
DOI: 10.1007/978-3-540-74936-3_37
Aparece en la colección:Actas de Congresos

Archivos en este elemento:
Archivo Descripción TamañoFormato 
C052_LNCS_DAGM07_postprint.pdfPostprint161,19 kBAdobe PDFObserva/Abre
Muestra el registro completo del elemento

Google ScholarTM



Este elemento está sujeto a una licencia Licencia Creative Commons Creative Commons