EasyDeepLearn

How does dropout work and when is it applied?

easy

Answer

  • During training, dropout randomly zeros a fraction p of activations per forward pass, forcing the network to distribute knowledge and not co-adapt.
  • At inference, all units are active and outputs are scaled (or scaling is done at train time — 'inverted dropout').
  • Common rates: 0.1-0.5.
  • Modern transformers use dropout in attention and MLP layers.
Check yourself — multiple choice
  • Dropout is applied only at inference
  • Dropout randomly zeros activations during training
  • Dropout replaces activations with random values at inference
  • Dropout is the same as weight decay

Dropout is a train-time regularization; inference uses the full network.

#regularization#training

Practise Deep Learning

214 interview questions in this topic.

Related questions