Adam: A Method for Stochastic Optimization
Adam automatically adjusts learning rates to guide neural-network training.
2014
267,799
Works
Selected research papers and books, linked to their authors.
Long Short-Term Memory
LSTM helps neural networks remember information over long sequences.
1997
164,520
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
Deep Learning
A textbook on neural networks, their mathematical foundations and practical applications.
2016
108,994
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Batch normalization rescales signals inside neural networks to speed up training.
2015
70,025
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
Dropout reduces memorization by switching off parts of a neural network during training.
2014
66,007
Learning Internal Representations by Error Propagation
Explained how networks learn internal representations by passing errors backward through layers.
1986
62,699
Auto-Encoding Variational Bayes
Variational autoencoders learn compact representations of data to generate new examples.
2014
62,453
Learning representations by back-propagating errors
Showed how passing errors backward through neural networks helps them learn useful patterns.
1986
53,096