Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by jeremyphoward on 2020-01-14 (UTC).

At @AiWamri medical imaging we often need to make a little data go a long way. One under-appreciated approach for this is self-supervised learning. It's almost magical!

I've written a little overview to help you get started. Let me know if you try it :)https://t.co/3mMZXcOuvQ

— Jeremy Howard (@jeremyphoward) January 14, 2020
learningtutorial
by ylecun on 2020-01-14 (UTC).

The best SSL approaches to learning visual features today use Siamese networks to learn embeddings.
Examples: two recent papers from FAIR, "Pretext-Invariant Representation Learning" (Misra et al.) and "MoCo" (He et al.). https://t.co/dYStkWA6Nw

— Yann LeCun (@ylecun) January 14, 2020
misc
by jeremyphoward on 2020-01-14 (UTC).

Oh, and if you're interested in giving this approach a try, we have a great dataset for you to test your ideas on: Image网 (pronounced "Imagewang). You can find the dataset here: https://t.co/IllPGz10Jg https://t.co/HPPrtgrUru pic.twitter.com/l3T5DBdIvt

— Jeremy Howard (@jeremyphoward) January 14, 2020
dataset
by jeremyphoward on 2020-01-21 (UTC).

I also added a link to @lilianweng's excellent overview post, in the 'further reading' section.https://t.co/N30sTMqfE3

— Jeremy Howard (@jeremyphoward) January 21, 2020
learningsurvey

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