Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.
, and .
CoRR (2015)

  • @dallmann
  • @hprop
  • @tgandor
  • @loroch
  • @analyst
  • @dblp
  • @spdrnl

rating distribution
average user rating4.5 out of 5.0 based on 1 review
  • userPicture
    14 hours ago (last updated 14 hours ago)
    Very readable, explaining both why and how BN works. Great build-up from the basics (activations, vanishing gradient, Internal Covariate Shift). It's no wonder, that Keras documentation links to it.
Please log in to take part in the discussion (add own reviews or comments).