Paper
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet, 2012): the result that launched deep learning
Krizhevsky, Sutskever and Hinton train a deep CNN on two GPUs and cut the ImageNet top-5 error from 26% to 15%, a margin that convinced the field — and Nvidia — that scale, GPUs and depth win. ReLUs, dropout and data augmentation all enter the standard toolkit here. 9 pages.
Companies in this report
