Analytical expressions for visual representations have been derived and they have been related to convolutional neural networks. In this document we want to verify the relationship between such representations and the CNNs. In order to accomplish this task we adopted a practical approach: we implemented a CNN and we ran several simulations with different configurations. Using the accuracy rating as measurement, we have been able to evaluate whether or not our changes were beneficial

Deep learning techniques applied in computer vision

Corsale, Federico
2017/2018

Abstract

Analytical expressions for visual representations have been derived and they have been related to convolutional neural networks. In this document we want to verify the relationship between such representations and the CNNs. In order to accomplish this task we adopted a practical approach: we implemented a CNN and we ran several simulations with different configurations. Using the accuracy rating as measurement, we have been able to evaluate whether or not our changes were beneficial
2017-04-13
deep learning, visual representations, Convolutional Neural Network, CNN
File in questo prodotto:
File Dimensione Formato  
federico_corsale_tesi.pdf

accesso aperto

Dimensione 2.28 MB
Formato Adobe PDF
2.28 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/25921