Please use this identifier to cite or link to this item:
Title: Analyzing state-of-the-art CNN’s explainability focusing on food classification
Author: Bergadà Salsen, Joan
Director/Tutor: Radeva, Petia
Ródenas Cumplido, Javier
Keywords: Xarxes neuronals convolucionals
Reconeixement òptic de formes
Treballs de fi de grau
Visió per ordinador
Aprenentatge automàtic
Convolutional neural networks
Optical pattern recognition
Computer software
Computer vision
Machine learning
Bachelor's theses
Issue Date: 21-Jun-2020
Abstract: [en] Convolutional Neural Networks (CNNs) are Deep Learning algorithms that can be applied to a wide range of environments with a high performance. We will study all the elements that form the CNNs, learn how they work, how to train them and how to diagnose its performance. We will also work the state-of-the-art visual explainability algorithms developing how they create their heatmaps. In the practical part we will use CNNs in order to classify food images into their classes and we will apply the studied explainability algorithms to understand the predictions made by the neural networks. Finally, we will perform a both qualitative and quantitative comparison between the explanations given by the applied algorithms.
Note: Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2020, Director: Petia Radeva i Javier Ródenas Cumplido
Appears in Collections:Treballs Finals de Grau (TFG) - Enginyeria Informàtica
Treballs Finals de Grau (TFG) - Matemàtiques

Files in This Item:
File Description SizeFormat 
tfg_joan_bergada_salsen.pdfMemòria63.49 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons