A moment-constrained neural network with a KL-divergence regularizer is presented as a maximum entropy method, though the regularizer is not a true entropy maximizer.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MEP-Net: Generating Solutions to Scientific Problems with Limited Knowledge by Maximum Entropy Principle
A moment-constrained neural network with a KL-divergence regularizer is presented as a maximum entropy method, though the regularizer is not a true entropy maximizer.