Home › Claude › aifoundations › alexnet_cnn_imagenet › Which technique randomly zeroes hidden neurons d…
Which technique randomly zeroes hidden neurons during training?
AWeight decay on the L2 norm
BStochastic depth of residual blocks
CBatch normalisation across the layer
DDropout with probability 0.5
Answer & Solution
Correct answer: D. Dropout with probability 0.5
Dropout sets each hidden neuron's output to zero with probability 0.5 during training. It forces neurons to learn robust features that cooperate with random subsets of others.
Related questions
Image similarity in AlexNet's last hidden layer is measured byThe SGD update rule for AlexNet usesRemoving any single middle convolutional layer of AlexNet costs roughlyAlexNet was trained for roughly how many epochs on ImageNet?At test time dropout is approximated byAlexNet uses overlapping pooling withAlexNet's second form of data augmentation isAlexNet's first form of data augmentation is