Rethinking graph transformers with spectral attention

D Kreuzer, D Beaini, W Hamilton… - Advances in …, 2021 - proceedings.neurips.cc
In recent years, the Transformer architecture has proven to be very successful in sequence
processing, but its application to other data structures, such as graphs, has remained limited …

Stacked deep dense neural network model to predict alzheimer's dementia using audio transcript data

YF Khan, B Kaushik, MKI Rahmani, ME Ahmed - Ieee Access, 2022 - ieeexplore.ieee.org
Alzheimer's disease (AD) is caused by cortical degeneration leading to memory loss and
dementia. A possible criterion for the early identification of Alzheimer's dementia is to identify …

A hybrid deep learning model using grid search and cross-validation for effective classification and prediction of suicidal ideation from social network data

A Chadha, B Kaushik - New generation computing, 2022 - Springer
Suicide deaths due to depression and mental stress are growing rapidly at an alarming rate.
People freely express their feelings and emotions on social network sites while they feel …

[Retracted] Convolutional Neural Network Face Recognition Method Using Fisher's Criterion

W Wang, F Wu - Mobile Information Systems, 2022 - Wiley Online Library
In order to further improve the ability of automatic feature extraction of deep learning
technology and better solve the problem of system recognition ability declining when the …

[图书][B] Guidage et planification réactive de trajectoire d'un drone monoculaire contrôlé par intelligence artificielle

A Duperré - 2020 - search.proquest.com
Le problème de guidage autonome est un domaine de recherche en constante évolution. La
popularisation des drones a étendu ce domaine de recherche au cours des dernières …

Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration

D Beaini, S Achiche, M Raison - arXiv preprint arXiv:2003.05182, 2020 - arxiv.org
Current research in convolutional neural networks (CNN) focuses mainly on changing the
architecture of the networks, optimizing the hyper-parameters and improving the gradient …

[图书][B] Perchage automatique de drones basé sur la vision artificielle

L Greffier - 2019 - search.proquest.com
L'utilisation de l'intelligence artificielle et de la vision se développe considérablement dans
l'industrie des drones, notamment pour la saisie ou le dépôt d'objets ou encore pour …