Skip to content

Instantly share code, notes, and snippets.

@frank-leap

frank-leap/coursera_deep_learning_3.md

Created December 21, 2017 20:08
Show Gist options
  • Save frank-leap/c3ea8194a6066c7d15bc3f55bcdaed26 to your computer and use it in GitHub Desktop.
Save frank-leap/c3ea8194a6066c7d15bc3f55bcdaed26 to your computer and use it in GitHub Desktop.
Download ZIP
coursera_deep_learning_3.md
Raw
coursera_deep_learning_3.md

orthogonalization: know what to tune to achieve what effect; for this would help to have orthogonal controls (steering wheel, acceleration, braking; well defined impact); however that's not usually the case in machine learning

assumptions we always made in ML:

  • fit training set well on cost function (human like): knobs would be: bigger network, better optimization algorithm (adam)
  • hope it does well in dev set: knobs would be: bigger (training) data set, regularization
  • hope it does well in test set: knob would be: bigger dev set
  • performs well in real world: k: change dev set or cost function
@frank-leap
Copy link
Author

Transfer learning: pre-training and fine tuning; a lot of low level features (detect edges, curves, positive objects...) can be reused

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment