Mutual Information, Neural Networks and the Renormalization Group — mentioned by rubidium

Thu, 29 Mar 2018 15:22:44 GMT

Obligatory arxiv link: https://arxiv.org/abs/1704.06279

Paper and discussion history. A mention is not an endorsement.

Mutual Information, Neural Networks and the Renormalization Group — mentioned by cs702

Fri, 25 Aug 2017 23:23:23 GMT

Thank you for posting this. Similar thoughts have been percolating in my stream-of-consciousness for a while, especially after coming across an earlier version of Tegmark & Lin's paper some months ago. My take is that deep neural nets work so well in practice because not all distributions of natural data are equally likely (and therefore, the no-free-lunch theorem(s), which assumes all distributions are equally likely, doesn't hold in the real world!); and that, in turn, is because the distribution of natural data is a consequence of the laws of Physics / symmetries of the universe in which…

Paper and discussion history. A mention is not an endorsement.

Mutual Information, Neural Networks and the Renormalization Group · HackerPapers discussions

Mutual Information, Neural Networks and the Renormalization Group — mentioned by rubidium

Mutual Information, Neural Networks and the Renormalization Group — mentioned by cs702