ImageNet Classification with Deep Convolutional Neural Networks

Like the large-vocabulary speech recognition paper we looked at yesterday, today's paper has also been described as a landmark paper in the history of deep learning. The ImageNet dataset contains over 1.5 million labeled high-resolution images of objects in roughly 22,000 categories. The annual ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) competition uses a subset of ImageNet with roughly 1000 images in each of 1000 categories. There are 1.2M training images, 50,000 validation images, and 150,000 testing images. For reporting error rates, a model predicts the top 5 most likely labels.