Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign
method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms …

We present a new algorithm to train a robust neural network against adversarial attacks. Our
algorithm is motivated by the following two ideas. First, although recent work has …

Neural random fields (NRFs), which are defined by using neural networks to implement
potential functions in undirected models, provide an interesting family of model spaces for …

How to sample training/validation data is an important question for machine learning
models, especially when the dataset is heterogeneous and skewed. In this paper, we …

Retina image analysis is an important screening tool for early detection of multiple diseases
such as diabetic retinopathy which greatly impairs visual function. Image analysis and …

Les recherches menées dans le cadre du présent mémoire de maitrise s' intéressent à
l'interaction entre les domaines d'études de l'intelligence artificielle et du droit de la propriété …

Validation accuracy and test accuracy are necessary, but not sufficient, measures of a neural
network classifier's quality. A model judged successful by these metrics alone may …

How and when can we depend on machine learning systems to make decisions for human-
being? This is probably the question everybody may (and should) ask before deploying …

Although deep neural networks (DNNs) could achieve state-of-the-art performance while
recognizing images, they often vulnerable to adversarial examples where input intended to …

Neural random fields (NRFs), referring to a class of generative models that use neural
networks to implement potential functions in random fields (aka energy-based models), are …