Mostrar el registro sencillo del ítem

dc.contributor.authorCruz, Edmanuel
dc.contributor.authorRangel, José Carlos
dc.contributor.authorGomez Donoso, Francisco
dc.contributor.authorBauer, Zuria
dc.contributor.authorCazorla, Miguel
dc.contributor.authorGarcía Rodríguez, José
dc.date.accessioned2019-12-17T20:50:46Z
dc.date.accessioned2019-12-17T20:50:46Z
dc.date.available2019-12-17T20:50:46Z
dc.date.available2019-12-17T20:50:46Z
dc.date.issued10/15/2018
dc.date.issued10/15/2018
dc.identifierhttps://ieeexplore.ieee.org/abstract/document/8489469/keywords#keywords
dc.identifier.issn2161-4407
dc.identifier.urihttps://ridda2.utp.ac.pa/handle/123456789/9438
dc.identifier.urihttps://ridda2.utp.ac.pa/handle/123456789/9438
dc.descriptionFor a robot, the ability to adapt his knowledge automatically and customize its behavior is a key feature. Furthermore, a robot should be able to carry out its tasks at a long-term basis, performing it seamlessly in presence of changes in their surroundings. To do that, it is essential that the robot dynamically learn from their environment, but to perform a fully retraining of a deep learning architecture when the model needs new knowledge is a highly time consuming task. This work focus on exploring several strategies to include new data to an already learned model, applied to the semantic localization problem focusing in the accuracy of the final model and their training time. Exhaustive experimentation is carried out and each result is discussed consequently.en_US
dc.description.abstractFor a robot, the ability to adapt his knowledge automatically and customize its behavior is a key feature. Furthermore, a robot should be able to carry out its tasks at a long-term basis, performing it seamlessly in presence of changes in their surroundings. To do that, it is essential that the robot dynamically learn from their environment, but to perform a fully retraining of a deep learning architecture when the model needs new knowledge is a highly time consuming task. This work focus on exploring several strategies to include new data to an already learned model, applied to the semantic localization problem focusing in the accuracy of the final model and their training time. Exhaustive experimentation is carried out and each result is discussed consequently.en_US
dc.formatapplication/pdf
dc.languageeng
dc.language.isoenen_US
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectRobotsen_US
dc.subjectSemanticsen_US
dc.subjectTrainingen_US
dc.subjectFeature extractionen_US
dc.subjectComputer architectureen_US
dc.subjectTask analysisen_US
dc.subjectVisualizationen_US
dc.subjectRobots
dc.subjectSemantics
dc.subjectTraining
dc.subjectFeature extraction
dc.subjectComputer architecture
dc.subjectTask analysis
dc.subjectVisualization
dc.titleFinding the Place: How to Train and Use Convolutional Neural Networks for a Dynamically Learning Roboten_US
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion


Ficheros en el ítem

FicherosTamañoFormatoVer

No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem