Deep Residual Learning for Image Recognition
ResNet, an image-recognition network, uses shortcuts between layers to make much deeper networks easier to train.
2016
353,189
Works
Selected research papers and books, linked to their authors.
Attention Is All You Need
The Transformer uses attention to translate text while allowing faster training.
2017
294,018
Adam: A Method for Stochastic Optimization
Adam automatically adjusts learning rates to guide neural-network training.
2014
267,799
ImageNet Classification with Deep Convolutional Neural Networks
AlexNet sharply improved image recognition with a deep neural network.
2012
202,088
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT learns word meaning from the text on both sides.
2018
192,498
Very Deep Convolutional Networks for Large-Scale Image Recognition
VGG networks improved image recognition by stacking more layers.
2014
167,467
Long Short-Term Memory
LSTM helps neural networks remember information over long sequences.
1997
164,520
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net outlines cells and other structures in biomedical images.
2015
153,640
Generative Adversarial Networks
GANs pit two networks against each other: one creates examples while the other learns to spot fakes.
2014
122,929
Deep learning
A review of how deep neural networks learn patterns in images, speech and text.
2015
122,734