University Sétif 1 FERHAT ABBAS Faculty of Sciences
Détail de l'auteur
Auteur Ahlem Drif |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Titre : Assessment explanation approaches for black box models Type de document : texte imprimé Auteurs : Khaled Bouabdallah, Auteur ; Seddik Boudissa, Auteur ; Ahlem Drif, Directeur de thèse Année de publication : 2022 Importance : 1 vol (79 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Artificial Intelligence
Explainable Artificial IntelligenceIndex. décimale : 004 Informatique Résumé :
Machine learning models, particularly deep learning models, are frequently referred to as ”black box models” due to their enormous complexity. Because of their lack of open- ness, they are difficult to understand and trust. To address this issue and create models with results that humans can understand, a subfield of artificial intelligence (AI) known as Ex- plainable Artificial Intelligence (XAI) was created. This thesis aims to provide an in-depth examination of XAI techniques as well as propose new approaches. We propose the Dis- criminitve Attention Guided Convolutional Neural Network (DAG-CNN), which focuses on lesion regions when making diagnoses and compares similarities between cases for thorax disease classification. This approach showed promising results with competitive accuracy and more explanation in comparison to other state-of-the-art solutions. We also proposed a grey-box model based on semi-supervised methodology utilizing a self-labeling framework that combines the advantages of both black-box and white-box models. The proposed self- labeling Grey-Box shows an accurate black-box classifier for labeling the unlabeled data and a white-box surrogate classifier for building an interpretable model.Côte titre : MAI/0575 En ligne : https://drive.google.com/file/d/1Qf6_zEg10-4tItJ2LU3ek8BrGRtkZE6M/view?usp=share [...] Format de la ressource électronique : Assessment explanation approaches for black box models [texte imprimé] / Khaled Bouabdallah, Auteur ; Seddik Boudissa, Auteur ; Ahlem Drif, Directeur de thèse . - 2022 . - 1 vol (79 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Artificial Intelligence
Explainable Artificial IntelligenceIndex. décimale : 004 Informatique Résumé :
Machine learning models, particularly deep learning models, are frequently referred to as ”black box models” due to their enormous complexity. Because of their lack of open- ness, they are difficult to understand and trust. To address this issue and create models with results that humans can understand, a subfield of artificial intelligence (AI) known as Ex- plainable Artificial Intelligence (XAI) was created. This thesis aims to provide an in-depth examination of XAI techniques as well as propose new approaches. We propose the Dis- criminitve Attention Guided Convolutional Neural Network (DAG-CNN), which focuses on lesion regions when making diagnoses and compares similarities between cases for thorax disease classification. This approach showed promising results with competitive accuracy and more explanation in comparison to other state-of-the-art solutions. We also proposed a grey-box model based on semi-supervised methodology utilizing a self-labeling framework that combines the advantages of both black-box and white-box models. The proposed self- labeling Grey-Box shows an accurate black-box classifier for labeling the unlabeled data and a white-box surrogate classifier for building an interpretable model.Côte titre : MAI/0575 En ligne : https://drive.google.com/file/d/1Qf6_zEg10-4tItJ2LU3ek8BrGRtkZE6M/view?usp=share [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0575 MAI/0575 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible
Titre : A Deep Learning Model For Collaborative Filtering Type de document : texte imprimé Auteurs : Ferkous, Mohamed Laid, Auteur ; Ahlem Drif, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (83 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems
Mutual Influence
Graph Attention NetworkIndex. décimale : 004 - Informatique Résumé :
Recommender systems have become an integral part of e-commerce sites and
other platforms such as social networking, movie/-music rendering websites. Network representation
learning have been used as a successful approaches to build efficient recommender
systems. However, learning the mutual influence generated by the contributions of each
node in the network is a challenging issue. In fact, the mutual influence carries collaborative
signals on user decisions helping to account for complex user-item interactions. For this
purpose, in this master thesis, we propose Multual Intercation Graph Attention Network
‘MIGAN” which is a new algorithm based on a the self-supervised representation learning
on large scale bipartite graph (BGNN). Experiments on real-world datasets demonstrate
that the proposed Graph learning method can achieve more accurate predictions and higher
recommendation efficiency.Côte titre : MAI/0522 En ligne : https://drive.google.com/file/d/1mGYDn5WsQu4tz8wXwWqFf3RXOFw_iyJV/view?usp=shari [...] Format de la ressource électronique : A Deep Learning Model For Collaborative Filtering [texte imprimé] / Ferkous, Mohamed Laid, Auteur ; Ahlem Drif, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (83 f .) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems
Mutual Influence
Graph Attention NetworkIndex. décimale : 004 - Informatique Résumé :
Recommender systems have become an integral part of e-commerce sites and
other platforms such as social networking, movie/-music rendering websites. Network representation
learning have been used as a successful approaches to build efficient recommender
systems. However, learning the mutual influence generated by the contributions of each
node in the network is a challenging issue. In fact, the mutual influence carries collaborative
signals on user decisions helping to account for complex user-item interactions. For this
purpose, in this master thesis, we propose Multual Intercation Graph Attention Network
‘MIGAN” which is a new algorithm based on a the self-supervised representation learning
on large scale bipartite graph (BGNN). Experiments on real-world datasets demonstrate
that the proposed Graph learning method can achieve more accurate predictions and higher
recommendation efficiency.Côte titre : MAI/0522 En ligne : https://drive.google.com/file/d/1mGYDn5WsQu4tz8wXwWqFf3RXOFw_iyJV/view?usp=shari [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0522 MAI/0522 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible