'Tree-AMP: Compositional Inference with Tree Approximate Message Passing', by Antoine Baker, Florent Krzakala, Benjamin Aubin, Lenka Zdeborová.

http://jmlr.org/papers/v24/20-695.html

#tree #models #entropy

Temperature check: theory and practice for training models with softmax-cross-entropy losses

Atish Agarwala, Samuel Stern Schoenholz, Jeffrey Pennington, Yann Dauphin

https://openreview.net/forum?id=LBA2Jj5Gqn

#softmax #entropy #models

Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization

David Peer, Bart Keulen, Sebastian Stabinger, Justus Piater, Antonio Rodriguez-sanchez

https://openreview.net/forum?id=LJohl5DnZf

#autoencoders #deep #entropy

Understanding is always proportional to the diversity of viewpoints that are captured. A great book attempts to capture this in linear form.

RT @nntaleb@twitter.com

A good book is one that no two readers would summarize in the same way. A great book is one that produces different summaries for the very same reader.

--------
#KolmogorovComplexity
#Entropy

🐦🔗: https://twitter.com/nntaleb/status/1616322596449959938

Temperature check: theory and practice for training models with softmax-cross-entropy losses

https://openreview.net/forum?id=LBA2Jj5Gqn

#softmax #entropy #learning