guillaume-chevalier/
A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the...
by Guillaume Chevalier Jupyter Notebook MIT licence 32 forks Created May 2018 View on GitHub
- Stars
- 148
- 2% of guillaume-chevalier's stars
- Rank
- #355,653
- of 851,992 repos, top 42%
- In Jupyter Notebook
- #8,112
- of 21,671 repos, top 38%
Among 851,992 repos
100–160 stars: 155,455 repos, including Linear-Attention-Recurrent-Neural-Network
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #353,585
- Next milestone
- +8 stars to reach the top 40%
- Popular
- One of 490,655 repos with 100+ stars
- Yearly average
- 17 stars a year since May 2018