by Michele Laurelli
Deep CNN that won ImageNet 2012, pioneering deep learning in computer vision.
8 layers (5 conv, 3 FC), ReLU activation, dropout, data augmentation. First to use GPU training at scale. Sparked deep learning revolution.
ImageNet 2012 winner
Deep learning breakthrough
GPU-accelerated training
A deep learning architecture specialized for processing grid-like data such as images, using convolutional layers.
Large-scale image dataset with 14M images across 20k categories, used for ILSVRC competition.
A subset of machine learning using neural networks with multiple layers to learn hierarchical representations of data.