Learning to Execute
State-of-the-art leaderboards
Greatest papers with code
Universal Transformers
ICLR 2019
• tensorflow/tensor2tensor
• 
Feed-forward and convolutional architectures have recently been shown to achieve superior results on some sequence modeling tasks such as machine translation, with the added advantage that they concurrently process all inputs in the sequence, leading to easy parallelization and faster training times.
Learning to Execute
• wojciechz/learning_to_execute
• 
Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train.