Home › Claude › aifoundations › alexnet_cnn_imagenet › AlexNet, per Krizhevsky et al., consists of how …
AlexNet, per Krizhevsky et al., consists of how many learned layers?
AFive layers in total
BEight layers in total
CSixteen layers in total
DThree layers in total
Answer & Solution
Correct answer: B. Eight layers in total
AlexNet has 8 learned layers: 5 convolutional + 3 fully-connected. The final FC layer feeds a 1000-way softmax for ImageNet classification.
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