Deep learning review and its applications


Autoria(s): Azkarate Saiz, Andoni
Contribuinte(s)

D'Anjou, Alicia

Ciencia de la Computación e Inteligencia Artificial/Konputazio Zientzia eta Adimen Artifiziala

Data(s)

08/10/2015

08/10/2015

08/10/2015

Resumo

Deep neural networks have recently gained popularity for improv- ing state-of-the-art machine learning algorithms in diverse areas such as speech recognition, computer vision and bioinformatics. Convolutional networks especially have shown prowess in visual recognition tasks such as object recognition and detection in which this work is focused on. Mod- ern award-winning architectures have systematically surpassed previous attempts at tackling computer vision problems and keep winning most current competitions. After a brief study of deep learning architectures and readily available frameworks and libraries, the LeNet handwriting digit recognition network study case is developed, and lastly a deep learn- ing network for playing simple videogames is reviewed.

Identificador

http://hdl.handle.net/10810/15792

Idioma(s)

eng

Relação

2015;1

Direitos

info:eu-repo/semantics/openAccess

Palavras-Chave #deep learning #machine learning #artificial neural network #visual recognition #object recognition #object mining #pattern recognition #computer vision #convolutional neural network #ca e
Tipo

info:eu-repo/semantics/masterThesis