Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by JeffDean on 2019-11-12 (UTC).

Nice new results from @GoogleAI researchers on improving the state-of-the-art on ImageNet!

"We...train a...model on...ImageNet...& use it as a teacher to generate pseudo labels on 300M unlabeled images. We then train a larger...model on the...labeled & pseudo labeled images." https://t.co/KGbKRkQt07

— Jeff Dean (@JeffDean) November 12, 2019
cvresearch
by srchvrs on 2019-11-13 (UTC).

They iteratively train several models. Largest is trained for 3.5 days on 2048-v3 TPU pod. It seems that one hour of this pod is ~$2.5K. Thus, we get an insane price tag ~$200K. The full experiment might cost you about half a MILLION USD if u want to reproduce it. https://t.co/wthQXaGe40

— Leonid Boytsov (@srchvrs) November 13, 2019
researchcv

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib