Deep Learning is Non-Equilibrium Information Dynamics
Carlos E. Perez

Thank you for your post.

I particularly like this :

The study of DL must be in the regime of non-equilibrium states and not in the mathematically convenient regime of equilibrium.

Could you confirm that I could add, because of the backpropagation process ?

Like what you read? Give Kouassi Konan Jean-Claude a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.