394 citations · 1.4k across the 25 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cond-mat.dis-nn2016★ 394 cited
Why does deep and cheap learning work so well?
Henry W. Lin, Max Tegmark, David Rolnick
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can appr…
cond-mat.dis-nn2016★ 37 cited
Criticality in Formal Languages and Statistical Physics
Henry W. Lin, Max Tegmark
We show that the mutual information between two symbols, as a function of the number of symbols between the two, decays exponentially in any probabilistic regular grammar, but can…