Document type

Bachelor thesis

Publication date

Publication license

memòria: cc-nc-nd (c) Joan Bergadà Salsen, 2020
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/183203

Analyzing state-of-the-art CNN’s explainability focusing on food classification

Journal Title

Journal ISSN

Volume Title

Related resource

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.

Description

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2020, Director: Petia Radeva i Javier Ródenas Cumplido

Citation

Citation

BERGADÀ SALSEN, Joan. Analyzing state-of-the-art CNN’s explainability focusing on food classification. [consulted: 6 of June of 2026]. Available at: https://hdl.handle.net/2445/183203

Export metadata

JSON - METS

Share record