no code implementations • 3 Apr 2023 • Sabri Boughorbel, Fethi Jarray, Abdulaziz Al Homaid, Rashid Niaz, Khalid Alyafei
In the experimental analysis, we show that mutli-modality improves the prediction performance compared with models trained solely on text or vital signs.
no code implementations • 6 Mar 2021 • Sabri Boughorbel, Fethi Jarray, Abdou Kadri
In this wo rk, we are interested in developing deep learning models for no-show prediction based on tabular data while ensuring fairness properties.
no code implementations • 27 Oct 2019 • Sabri Boughorbel, Fethi Jarray, Neethu Venugopal, Shabir Moosa, Haithum Elhadi, Michel Makhlouf
We propose a new FL model called Federated Uncertainty-Aware Learning Algorithm (FUALA) that improves on Federated Averaging (FedAvg) in the context of EHR.
no code implementations • 24 Nov 2018 • Sabri Boughorbel, Fethi Jarray, Neethu Venugopal, Haithum Elhadi
The network is alternately trained on epochs with the clean dataset with a simple cross-entropy loss and on next epoch with the noisy dataset and a loss corrected with the estimated corruption matrix.
no code implementations • 11 Jul 2013 • Bilel Ben Ali, Fethi Jarray
With the growing number of textual resources available, the ability to understand them becomes critical.