Passer au contenu

/ Département d'informatique et de recherche opérationnelle

Je donne

Rechercher

Thèses et mémoires

Des thèses et mémoires de nos étudiants sont conservés et consultables dans Papyrus, le dépôt institutionnel de l'Université de Montréal.

 

 

For a detailed search
Visit Papyrus
Date Sort by date in descending order Title Sort by title in descending order
2023-10 Training large multimodal language models with ethical values
2009-08 Training deep convolutional architectures for vision
2020-01 Traffic prediction and bilevel network design
2012-07 Traduction statistique vers une langue à morphologie riche : combinaison d’algorithmes de segmentation morphologique et de modèles statistiques de traduction automatique
2010-08 Traduction statistique par recherche locale
2023-04 Toward trustworthy deep learning : out-of-distribution generalization and few-shot learning
2020-11 Towards using intelligent techniques to assist software specialists in their tasks
2020-01 Towards using fluctuations in internal quality metrics to find design intents
2019-08 Towards Understanding Generalization in Gradient-Based Meta-Learning
2023-06 Towards the reduction of greenhouse gas emissions : models and algorithms for ridesharing and carbon capture and storage
2020-08 Towards privacy preserving cooperative cloud based intrusion detection systems
2023-07 Towards privacy-preserving and fairness-enhanced item ranking in recommender systems
2022-09 Towards meaningful and data-efficient learning : exploring GAN losses, improving few-shot benchmarks, and multimodal video captioning
2019-07 Towards learning sentence representation with self-supervision
2021-08 Towards fairness in Kidney Exchange Programs
2020-12 Towards deep unsupervised inverse graphics
2016-05 Towards deep semi supervised learning
2021-08 Towards computationally efficient neural networks with adaptive and dynamic computations
2023-12 Towards combining deep learning and statistical relational learning for reasoning on graphs
2021-10 Towards causal federated learning : a federated approach to learning representations using causal invariance