Neural Estimator of Information for Time-Series Data with Dependency

Neural Estimator of Information for Time-Series Data with Dependency

Novel approaches to estimate information measures using neural networks are well-celebrated in recent years both in the information theory and machine learning communities. These neural-based estimators are shown to converge to the true values when estimating mutual information and conditional mutua...

Full description

Bibliographic Details
Main Authors: Sina Molavipour, Hamid Ghourchian, Germán Bassi, Mikael Skoglund
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Entropy
Subjects:
neural networks
conditional mutual information
directed information
Markov source
variational bound
Online Access:https://www.mdpi.com/1099-4300/23/6/641

Internet

https://www.mdpi.com/1099-4300/23/6/641

Similar Items