no code implementations • 11 Dec 2023 • MohammadReza Davari, Eugene Belilovsky
These breadcrumbs are constructed by subtracting the weights from a pre-trained model before and after fine-tuning, followed by a sparsification process that eliminates weight outliers and negligible perturbations.
no code implementations • 21 May 2023 • Zachary Yang, Yasmine Maricar, MohammadReza Davari, Nicolas Grenon-Godbout, Reihaneh Rabbany
Detecting toxicity in online spaces is challenging and an ever more pressing problem given the increase in social media and gaming consumption.
1 code implementation • 26 Mar 2023 • Nader Asadi, MohammadReza Davari, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky
Class prototypes are evolved continually in the same latent space, enabling learning and prediction at any point.
no code implementations • 28 Oct 2022 • MohammadReza Davari, Stefan Horoi, Amine Natik, Guillaume Lajoie, Guy Wolf, Eugene Belilovsky
Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different ways.
no code implementations • CVPR 2022 • MohammadReza Davari, Nader Asadi, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks.
no code implementations • COLING 2020 • MohammadReza Davari, Leila Kosseim, Tien Bui
In this paper, we propose an approach to automate the process of place name detection in the medical domain to enable epidemiologists to better study and model the spread of viruses.
no code implementations • 24 Apr 2019 • MohammadReza Davari, Leila Kosseim, Tien D. Bui
These results underline the importance of domain specific embedding as well as specific linguistic features in toponym detection in medical journals.