2 papers
cs.IT2024
Semantic Information G Theory for Range Control with Tradeoff between Purposiveness and Efficiency
Chenguang Lu
Recent advances in deep learning suggest that we need to maximize and minimize two different kinds of information simultaneously. The Information Max-Min (IMM) method has been used…
cs.LG2024
Semantic Variational Bayes Based on Semantic Information G Theory for Solving Latent Variables
Chenguang Lu
The Variational Bayesian method (VB) is used to solve the probability distributions of latent variables with the minimum free energy criterion. This criterion is not easy to unders…