Claude alexnet_cnn_imagenet — practice questions
15 free MCQs with worked solutions. Tap any question for the answer + explanation, or practice them all in the app.
Practice Claude alexnet_cnn_imagenet in the app →AlexNet, per Krizhevsky et al., consists of how many learned layers?The nonlinearity used after every convolutional and FC layer isWhich technique randomly zeroes hidden neurons during training?AlexNet's input image size isThe final softmax layer in AlexNet outputs distributions overAlexNet has roughly how many learnable parameters?Why are ReLU networks faster to train than tanh networks?AlexNet's first form of data augmentation isAlexNet's second form of data augmentation isAlexNet uses overlapping pooling withAt test time dropout is approximated byAlexNet was trained for roughly how many epochs on ImageNet?Removing any single middle convolutional layer of AlexNet costs roughlyThe SGD update rule for AlexNet usesImage similarity in AlexNet's last hidden layer is measured by