Direct language-to-language sentence translation. State-of-the-art accuracy with a simple, language-agnostic architecture.
Facebook's memory-oriented neural system. One of two novel architectures which explore a topology beyond feed-forward lattices of neurons.
Baidu's speech recognition engine. Proved purely deep-learned networks can beat hand-tuned systems.
Variational autoencoder. An efficient, generative model for feature learning.
Image classifier from Microsoft Research Asia. Dramatically increased the practical depth of convolutional networks. ILSVRC 2015 winner.
Image classifier demonstrating the power of small convolutional filters. ILSVRC 2014 winner.
Image classifier. Watershed for deep learning by beating hand-tuned image systems at ILSVRC 2012.
Atari-playing neural network from DeepMind. Achieves superhuman performance on majority of Atari2600 games, without any preconceptions.