Skip to content

Instantly share code, notes, and snippets.

@fran0x

fran0x/coursera_deep_learning_3.md

Created December 21, 2017 20:08
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save fran0x/c3ea8194a6066c7d15bc3f55bcdaed26 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save fran0x/c3ea8194a6066c7d15bc3f55bcdaed26 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. fran0x created this gist Dec 21, 2017.
    8 changes: 8 additions & 0 deletions coursera_deep_learning_3.md
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,8 @@
    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