M
Mohamed Ishmael Belghazi
Researcher at Facebook
Publications - 8
Citations - 1001
Mohamed Ishmael Belghazi is an academic researcher from Facebook. The author has contributed to research in topics: Multivariate random variable & Mutual information. The author has an hindex of 5, co-authored 8 publications receiving 662 citations. Previous affiliations of Mohamed Ishmael Belghazi include HEC Montréal.
Papers
More filters
Proceedings Article
Mutual Information Neural Estimation.
Mohamed Ishmael Belghazi,Aristide Baratin,Sai Rajeshwar,Sherjil Ozair,Yoshua Bengio,Aaron Courville,Devon Hjelm +6 more
TL;DR: A Mutual Information Neural Estimator (MINE) is presented that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent, and applied to improve adversarially trained generative models.
Proceedings Article
Mine: mutual information neural estimation
Mohamed Ishmael Belghazi,Aristide Baratin,Sai Rajeswar,Sherjil Ozair,Yoshua Bengio,Aaron Courville,Devon Hjelm +6 more
Posted Content
Hierarchical Adversarially Learned Inference
Mohamed Ishmael Belghazi,Sai Rajeswar,Olivier Mastropietro,Negar Rostamzadeh,Jovana Mitrovic,Aaron Courville +5 more
TL;DR: A novel hierarchical generative model with a simple Markovian structure and a corresponding inference model that supports the learning of progressively more abstract representations as well as providing semantically meaningful reconstructions with different levels of fidelity is proposed.
Posted Content
Learning about an exponential amount of conditional distributions
TL;DR: Neural Conditioner (NC) as discussed by the authors is a self-supervised machine that can learn about all the conditional distributions of a random vector and auto-encode examples for downstream classification tasks.
Proceedings Article
Learning about an exponential amount of conditional distributions
TL;DR: The NC integrates different self-supervised tasks (each being the estimation of a conditional distribution) and levels of supervision (partially observed data) seamlessly into a single learning experience.