Google used reinforcement learning to design next-gen AI accelerator chips (venturebeat.com) 2 points by matmatmatmat 5y ago ↗ HN
[–] adipandas 5y ago ↗ I think recently RL or DL is going crazy with design. This is very nice to see.https://www.nature.com/articles/d41586-021-01515-9
1 comment
[ 3.7 ms ] story [ 15.1 ms ] threadhttps://www.nature.com/articles/d41586-021-01515-9