Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/151211
Title: | Contributions to explainable deep learning models |
Author: | Adhane, Gereziher ![]() |
Director: | Masip Rodó, David ![]() Dehshibi, Mohammad Mahdi ![]() |
Abstract: | In this work, we propose techniques to enhance the performance and transparency of convolutional neural networks (CNNs). We introduce novel methods for informative sample selection (ISS), uncertainty quantification, and visual explanation. The two ISS methods involve using reinforcement learning to filter out samples that could lead to overfitting and bias, and employing Monte Carlo dropout to estimate model uncertainty during training and inference. In addition, we present two visual explainability techniques: ADVISE, which generates detailed visual explanations and quantifies the relevance of feature map units, and UniCAM, which explains the opaque nature of knowledge distillation. These methods aim to improve model accuracy, robustness, fairness, and explainability, contributing to both academic research and the transparency of CNNs in computer vision applications. |
Keywords: | explainable AI transparency model uncertainty sample selection visual explainability |
Document type: | info:eu-repo/semantics/doctoralThesis |
Issue Date: | 10-Jul-2024 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ ![]() |
Appears in Collections: | Tesis doctorals |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
PhD_Thesis.pdf | Gereziher_dissertation | 13,54 MB | Adobe PDF | ![]() View/Open |
Share:


This item is licensed under aCreative Commons License