Fast and Easy Infinitely Wide Networks with Neural Tangents (ai.googleblog.com) 15 points by rainboiboi 6y ago ↗ HN
[–] dgreensp 6y ago ↗ Can someone explain the implications of this for performance, or what we can do now that we couldn’t do before? [–] perl4ever 6y ago ↗ Well, they seem to be claiming it allows insight or understanding into how the networks work. However, they don't seem to demonstrate that as such.
[–] perl4ever 6y ago ↗ Well, they seem to be claiming it allows insight or understanding into how the networks work. However, they don't seem to demonstrate that as such.
[–] rllin 6y ago ↗ It really looks more and more like JAX is the internal winner after the tf 2.0 fiasco [–] [dead] miscPerson 6y ago ↗ For the contextless, what was the TF 2.0 fiasco?
4 comments
[ 2.7 ms ] story [ 23.2 ms ] thread