osmarks/documentation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Edit ‘the_seventy_maxims_of_maximally_effective_machine_learning_engineers’

Browse Source
This commit is contained in:
osmarks 2025-03-02 11:05:39 +00:00 committed by wikimind
parent 4edc137aa0
commit 2e1219c4fb
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
View File

@ -3,7 +3,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
*. Preprocess, then train. *. Preprocess, then train.
*. A training loop in motion outranks a perfect architecture that isn’t implemented. *. A training loop in motion outranks a perfect architecture that isn’t implemented.
*. A debugger with a stack trace outranks everyone else. *. A debugger with a stack trace outranks everyone else.
*. Regularization covers a multitude of overfitting sins. *. Regularization covers a multitude of sins.
*. Feature importance and data leakage should be easier to tell apart. *. Feature importance and data leakage should be easier to tell apart.
*. If increasing model complexity wasn’t your last resort, you failed to add enough layers. *. If increasing model complexity wasn’t your last resort, you failed to add enough layers.
*. If the accuracy is high enough, stakeholders will stop complaining about the compute costs. *. If the accuracy is high enough, stakeholders will stop complaining about the compute costs.