Home › Claude › aifoundations › alexnet_cnn_imagenet › AlexNet has roughly how many learnable parameters?
AlexNet has roughly how many learnable parameters?
AAbout 600 million parameters
BAbout 6 thousand parameters
CAbout 6 million parameters
DAbout 60 million parameters
Answer & Solution
Correct answer: D. About 60 million parameters
Roughly 60 million parameters across the 8 learned layers, dominated by the fully-connected layers. This was why overfitting was a major concern that dropout and data augmentation addressed.
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