New answers tagged dropout
1
vote
Is it mandatory to multiply every activation of a layer by droupout factor during testing?
There are two types of dropout, depending on whether a scaling correction is applied during:
testing - without dropout applied, to decrease logits by a factor $1-p$ to match the expected magnitude ...
Top 50 recent answers are included
Related Tags
dropout × 26neural-networks × 13
deep-learning × 8
regularization × 8
machine-learning × 6
convolutional-neural-networks × 5
training × 4
overfitting × 4
long-short-term-memory × 3
testing × 3
reinforcement-learning × 2
keras × 2
accuracy × 2
generalization × 2
tensorflow × 1
q-learning × 1
deep-rl × 1
recurrent-neural-networks × 1
dqn × 1
proofs × 1
monte-carlo-methods × 1
linear-regression × 1
relu × 1
legal × 1
google × 1