A paper a day will have you screaming hurray

Day 12: Generating Long Sequences with Sparse Transformers

Day 10: All You Need Is A Good Init

[Nov 19, 2015] How to initialize your deep networks for any activation function

Day 9: Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Day 8: Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification (Kaiming…

Day 7: Natural TTS Synthesis By Conditioning WaveNet On Mel Spectogram Predictions (Tacotron 2)

Day 6: Deep Voice 3: Scaling Text to Speech with Convolutional Sequence Learning

[Oct 20, 2017] Real-time, high quality, multi-speaker text-to-speech inference

Day 5: Conditional Image Generation with PixelCNN Decoders

Day 4: Pixel Recurrent Neural Networks

[Jan 25, 2016] Generating images with RNN’s

TL-DR

Day 3: WaveNet: A Generative Model for Raw Audio