Modern Deep Learning & Transformers

Alex Krizhevsky

Built AlexNet in 2012 with Ilya Sutskever and Geoffrey Hinton, the deep convolutional network whose ImageNet win is widely credited with kicking off the deep learning boom.

Alex Krizhevsky built AlexNet as a graduate student under Geoffrey Hinton at the University of Toronto, together with Ilya Sutskever. Entered in the 2012 ImageNet competition, it beat every existing hand-engineered computer vision pipeline by a wide margin — roughly halving the previous best error rate — and is now widely treated as the single result that convinced the rest of the field deep learning was worth taking seriously again.

The result depended as much on engineering as on the architecture itself: Krizhevsky implemented the training in raw CUDA and split the network across two GPUs to fit it in memory, at a time when training a network this size on GPUs at all was still unusual. That combination — a deep CNN, ReLU activations, dropout, and GPU training done well enough to be practical — became the template computer vision followed for years afterward.

He largely stepped back from AI research in the years after, but the paper's influence didn't need him to: AlexNet is one of the most-cited papers in computer science, and the "just add more compute and data" lesson it demonstrated echoes through every scaling result that followed it.

See also: Geoffrey Hinton, Ilya Sutskever

Learn more: Computer Vision · History & Landscape

Mentioned in

Lessons where this comes up in context.