Hacker News
- AdamW and Super-convergence is now the fastest way to train neural nets http://www.fast.ai/2018/07/02/adam-weight-decay/ 37 comments
Linking pages
- Super-Convergence with JUST PyTorch https://www.kamwithk.com/super-convergence-with-just-pytorch-ck6k9tkbo0139d9s1bvdlfp58 6 comments
- Text Summarization, Part 3 — Data Pipeline and Results | by Mohamed Bamouh | Besedo Engineering Blog | Medium https://medium.com/besedo-engineering/text-summarization-part-3-data-pipeline-and-results-3bb83c715304 0 comments