NN training goes through two distinct phases: (1) reducing classification error through drift (2) optimally compressing mutual information of hidden layers through diffusion https://arxiv.org/abs/1703.00810 pic.twitter.com/He7dNY3NSv
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
they mention later on that they also do the analysis for cases with no symmetries
the high signal -> high noise transition in training is also general afaict in the couple of DL projects I've tried, NNs do in general seem to keep improving after a clear signal is gone
If I’m reading right that they’ve spun a general theory of DL based on runs discriminating inside/outside of a hypersphere, everyone should be laughing at them.
I’m not sure what is in the supplementary material (can’t easily find) but based on this bit, sounds like all studies were done with trivial synthetic data. If so this is a nice intro class project, not a publishable result, much less a breakthrough.pic.twitter.com/msWSGp9NM8
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.