Article,

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.

, and .
CoRR, (2015)

Meta data

Tags

Users

  • @ogerst
  • @fabiusk
  • @dallmann
  • @hprop
  • @msteininger
  • @tgandor
  • @loroch
  • @analyst
  • @cmcneile
  • @cpankow
  • @dblp
  • @spdrnl

Comments and Reviewsshow / hide

  • @tgandor
    6 years ago (last updated 6 years 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).