440 citations · 467 across the 5 of their papers we have counts for
5 papers
What classifiers know what they don't?
Mohamed Ishmael Belghazi, David Lopez-Paz
Being uncertain when facing the unknown is key to intelligent decision making. However, machine learning algorithms lack reliable estimates about their predictive uncertainty. This…
Learning about an exponential amount of conditional distributions
Mohamed Ishmael Belghazi, Maxime Oquab, Yann LeCun +1
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector . The NC is a function $NC(x \cdot a…
Hierarchical Adversarially Learned Inference
Mohamed Ishmael Belghazi, Sai Rajeswar, Olivier Mastropietro +3
We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using th…
MINE: Mutual Information Neural Estimation
Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar +4
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutua…
Conservativeness of untied auto-encoders
Daniel Jiwoong Im, Mohamed Ishmael Diwan Belghazi, Roland Memisevic
We discuss necessary and sufficient conditions for an auto-encoder to define a conservative vector field, in which case it is associated with an energy function akin to the unnorma…