AlexNet used GPUs to train a deep convolutional network on ImageNet and won the 2012 ImageNet competition by a large margin.

Format Online paper / PDF

Location PART 1 - TONS OF PUNKS, ONE BIG JERK CHAPTER 4: KEYSTROKES AND BRUSHSTROKES Understanding the Medium

"AlexNet used GPUs to train a deep convolutional network on ImageNet and won the 2012 ImageNet competition by a large margin."

The paper reports an efficient GPU implementation and a winning ILSVRC-2012 top-5 error rate of 15.3 percent versus 26.2 percent for the second-best entry.

View Source

Source title ImageNet Classification with Deep Convolutional Neural Networks

Source authors Alex Krizhevsky; Ilya Sutskever; Geoffrey E. Hinton

Source year 2012

Confidence high

Importance high