1991: NN learns to program NN fast. 2021: NN learns to program Transformers fastpeople.idsia.ch·2 pts·jbesomi·0
Extracting Structured Data from Recipes Using Conditional Random Fields (2015)open.blogs.nytimes.com·2 pts·jbesomi·0
Switch Transformers: Scaling to Trillion Parameter Models with Simple Sparsityarxiv.org·2 pts·jbesomi·0
C. Manning, P. Raghavan and H. Schütze, Introduction to Information Retrievalnlp.stanford.edu·2 pts·jbesomi·0
Making instagram.com faster: Code size and execution optimizationsinstagram-engineering.com·1 pts·jbesomi·0