Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on DeepMind achieves SOTA image recognition with 8.7x faster training. Parent comment
"guess and check" is terribly ineffective with multi-day training runs. Brings us right back to the batch processing paradigm of the 1960s.
There are no comments on this comment yet.
"guess and check" is terribly ineffective with multi-day training runs. Brings us right back to the batch processing paradigm of the 1960s.