SESK: Stuff Everyone Should Know · sesk.info/ai-alexnet-60-million
About how many parameters did AlexNet, the 2012 ImageNet breakthrough network, have?
About 60 million.
- About 60 thousand
- About 60 million ✔
- About 60 billion
Why: Krizhevsky, Sutskever and Hinton's network had 60 million parameters and five convolutional layers. An efficient GPU implementation helped make its training faster.
Huh, didn't know that: It learned from about 1.3 million ImageNet training images sorted into 1,000 classes.
AlexNet had 60 million parameters. I have trouble with three parameters for dinner.
Like this card?
References
Answer: About 60 million. Krizhevsky, Sutskever and Hinton's network had 60 million parameters and five convolutional layers. An efficient GPU implementation helped make its training faster.
- NeurIPS 2012: ImageNet Classification with Deep Convolutional Neural Networks (abstract) papers.nips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers
Checked 2026-10-10.
Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.
More stuff everyone should know
Artificial IntelligenceWhat did AlexNet's authors use to reduce overfitting in its fully connected layers?Artificial IntelligenceImageNet's millions of labeled images are organized by which word hierarchy?Artificial IntelligenceWhich of these is a hyperparameter you set, not something the model learns?
That's stuff everyone should know.