Deep ensembles perform better than a single network thanks to the diversity among their
members. Recent approaches regularize predictions to increase diversity; however, they …

Reinforcement Learning (RL) environments can produce training data with spurious
correlations between features due to the amount of training data or its limited feature …

In this article, a modified mutual information maximization (InfoMax) framework, named
channel capacity maximization (CapMax), is proposed and applied to learn informative …

Recently, several methods have been proposed for estimating the mutual information from
sample data using deep neural networks. This approach is referred to as (). s differ from …

Correlations between factors of variation are prevalent in real-world data. Exploiting such
correlations may increase predictive performance on noisy data; however, often correlations …

Novel approaches to estimate information measures using neural networks are well-
celebrated in recent years both in the information theory and machine learning communities …

Abstract Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose
tools from information theory that are able to naturally measure the statistical dependencies …

Recently, several methods have been proposed for estimating the mutual information from
sample data using deep neural networks. These estimators ar referred to as neural mutual …

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 …

Использование нейронных сетей для аппроксимации исследуемой функции
предложено в [1]. Было показано, что в рамках модели однослойной нейронной сети …