Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature …
C Yang, H Wen, B Hooi, L Zhou - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
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 …
B Duong, T Nguyen - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
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 …