52 citations · 153 across the 67 of their papers we have counts for
7 papers · 1 filter
Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
Abdelrahman Zayed, Prasanna Parthasarathi, Goncalo Mordido +3
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, us…
Local Structure Matters Most in Most Languages
Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq +1
Many recent perturbation studies have found unintuitive results on what does and does not matter when performing Natural Language Understanding (NLU) tasks in English. Coding prope…
Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes
Louis Clouâtre, Prasanna Parthasarathi, Amal Zouaq +1
Providing better language tools for low-resource and endangered languages is imperative for equitable growth. Recent progress with massively multilingual pretrained models has prov…
SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness
Gonçalo Mordido, Sébastien Henwood, Sarath Chandar +1
Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods t…
Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
Enamundram Naga Karthik, Anne Kerbrat, Pierre Labauge +8
Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent years. However, most methods tend to be s…
Improving Meta-Learning Generalization with Activation-Based Early-Stopping
Simon Guiroy, Christopher Pal, Gonçalo Mordido +1
Meta-Learning algorithms for few-shot learning aim to train neural networks capable of generalizing to novel tasks using only a few examples. Early-stopping is critical for perform…
Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers
Amir Ardalan Kalantari, Mohammad Amini, Sarath Chandar +1
Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many curre…