Výsledky vyhledávání - "Abhari, Sara"

Report

Deep Unlearn: Benchmarking Machine Unlearning

Autor: Cadet, Xavier F., Borovykh, Anastasia, Malekzadeh, Mohammad, Ahmadi-Abhari, Sara, Haddadi, Hamed

Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in light of data privacy requirements, trustworthiness, and safety in deplo

Externí odkaz: http://arxiv.org/abs/2410.01276

Zobrazit plný text záznamu

Report

A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment

Autor: Cadet, Xavier F., Aloufi, Ranya, Ahmadi-Abhari, Sara, Haddadi, Hamed

Automating dysarthria assessments offers the opportunity to develop practical, low-cost tools that address the current limitations of manual and subjective assessments. Nonetheless, the small size of most dysarthria datasets makes it challenging to d

Externí odkaz: http://arxiv.org/abs/2306.04337

Zobrazit plný text záznamu

Report

Evaluating The Robustness of Self-Supervised Representations to Background/Foreground Removal

Autor: Cadet, Xavier F., Aloufi, Ranya, Miranville, Alain, Ahmadi-Abhari, Sara, Haddadi, Hamed

Despite impressive empirical advances of SSL in solving various tasks, the problem of understanding and characterizing SSL representations learned from input data remains relatively under-explored. We provide a comparative analysis of how the represe

Externí odkaz: http://arxiv.org/abs/2306.01398

Zobrazit plný text záznamu

Akademický článek

Indirect effect of extra-industry network and innovativeness on performance through proactiveness

Autor: Jalali, Alireza, Abhari, Sara, Jaafar, Mastura

Publikováno v: Journal of Facilities Management, 2022, Vol. 22, Issue 3, pp. 382-401.

Externí odkaz: http://www.emeraldinsight.com/doi/10.1108/JFM-02-2022-0019

Zobrazit plný text záznamu

Report

FIB: A Method for Evaluation of Feature Impact Balance in Multi-Dimensional Data

Autor: Cadet, Xavier F., Ahmadi-Abhari, Sara, Haddadi, Hamed

Errors might not have the same consequences depending on the task at hand. Nevertheless, there is limited research investigating the impact of imbalance in the contribution of different features in an error vector. Therefore, we propose the Feature I

Externí odkaz: http://arxiv.org/abs/2207.04500

Zobrazit plný text záznamu