Improved neural networks based on mutual information via information geometry

DOI10.3390/a12050103zbMath1461.68201OpenAlexW2945368966MaRDI QIDQ2004876

Yanyan Li

Publication date: 7 October 2020

Published in: Algorithms (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3390/a12050103

zbMATH Keywords

neural networksinformation geometrygeodesic line

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Statistical aspects of information-theoretic topics (62B10) Information geometry (statistical aspects) (62B11)

Uses Software

• darch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Information geometry. Near randomness and near independence
• Asymptotic methods in statistical decision theory
• The relation between information theory and the differential geometry approach to statistics
• Conjugate gradient type methods for unsymmetric and inconsistent systems of linear equations
• Statistical tests based on geodesic distances
• Information geometry of estimating functions in semi-parametric statistical models
• A novel information geometric approach to variable selection in MLP networks
• Reducing the Dimensionality of Data with Neural Networks
• Information geometry on hierarchy of probability distributions
• Science from Fisher Information
• Evolving Neural Network Ensembles by Minimization of Mutual Information
• Natural Gradient Learning Algorithms for RBF Networks
• A Fast Learning Algorithm for Deep Belief Nets