Skip to content
ml-recall

#internal-covariate-shift

1 question from Training Deep Networks

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: True or false

mediumAI-checkedTraining Deep Networks

Batch normalization was introduced as a way to reduce internal covariate shift, the change in each layer's input distribution during training. True or false: later controlled experiments confirmed that reducing this shift is the main reason batch normalization speeds up training.

Choose one option