Beta. Content is under active construction and has not been peer-reviewed. Report errors on GitHub.Disclaimer

Dropout

1 questionsDifficulty 4-4View topic
Intermediate
0 / 1
1 intermediateAdapts to your performance
1 / 1
intermediate (4/10)conceptual
Dropout randomly zeros each neuron's activation with probability during training. At test time, activations are multiplied by (or equivalently, training activations are scaled by ). Why is this scaling necessary?