Dice: Diversity in deep ensembles via conditional redundancy adversarial estimation

A Rame, M Cord - arXiv preprint arXiv:2101.05544, 2021 - arxiv.org
Deep ensembles perform better than a single network thanks to the diversity among their
members. Recent approaches regularize predictions to increase diversity; however, they …

[HTML][HTML] Neural estimator of information for time-series data with dependency

S Molavipour, H Ghourchian, G Bassi, M Skoglund - Entropy, 2021 - mdpi.com
Novel approaches to estimate information measures using neural networks are well-
celebrated in recent years both in the information theory and machine learning communities …

Statistical inference of information in networks: Causality and directed information graphs

S Molavipour - 2021 - diva-portal.org
Over the last decades, the advancements in measurement, collection, and storage of data
have provided tremendous amounts of information. Thus, it has become crucial to extract …