vene / sparse-structured-attention
Sparse and structured neural attention mechanisms
☆224Updated 4 years ago
Related projects: ⓘ
- Latent Alignment and Variational Attention☆326Updated 5 years ago
- VQ-VAE implementation / pytorch☆181Updated 6 years ago
- Adaptive Softmax implementation for PyTorch☆79Updated 5 years ago
- Code for Sluice networks: Learning what to share between loosely related tasks☆152Updated 5 years ago
- Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun☆400Updated 4 years ago
- Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"☆165Updated 5 years ago
- Recurrent Variational Autoencoder with Dilated Convolutions that generates sequential data implemented in pytorch☆72Updated 3 years ago
- ☆155Updated 6 years ago
- An implementation of DeepMind's Relational Recurrent Neural Networks (NeurIPS 2018) in PyTorch.☆244Updated 5 years ago
- meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)☆110Updated 2 years ago
- Code to accompany the paper "Learning Graphical State Transitions"☆170Updated 7 years ago
- Implementation of Sparsemax activation in Pytorch☆155Updated 4 years ago
- Code for the Eager Translation Model from the paper You May Not Need Attention☆293Updated 5 years ago
- Codes for "Towards Binary-Valued Gates for Robust LSTM Training".☆76Updated 6 years ago
- Tools for PyTorch☆221Updated 2 years ago
- SparseMAP: differentiable sparse structure inference☆110Updated 5 years ago
- Dynamic evaluation for pytorch language models, now includes hyperparameter tuning☆105Updated 6 years ago
- Implementation of VLAE☆215Updated 6 years ago
- Sparse Variational Dropout, ICML 2017☆309Updated 4 years ago
- ☆64Updated 6 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆212Updated 6 years ago
- PyTorch implementation of Global Vectors for Word Representation.☆92Updated 6 years ago
- NEG loss implemented in pytorch☆125Updated 7 years ago
- Cleaned original source code from my NIPS publication☆154Updated 6 years ago
- Good Semi-Supervised Learning That Requires a Bad GAN☆182Updated 6 years ago
- A PyTorch implementation of : Language Modeling with Gated Convolutional Networks.☆100Updated 2 years ago
- ReGAN: Sequence GAN using RE[INFORCE|LAX|BAR] based PG estimators☆41Updated 6 years ago
- Code for Structured Attention Networks https://arxiv.org/abs/1702.00887☆235Updated 7 years ago
- ☆78Updated 6 years ago
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks (ICLR 2018)☆124Updated last year