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
2025-10-03 11:01:19 +00:00
committed by wikimind
parent a6550f918b
commit 88c415a14a
1 changed files with 1 additions and 1 deletions
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

@@ -14,7 +14,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
*. A gentle learning rate turneth away divergence. Once the loss stabilizes, crank it up. *. A gentle learning rate turneth away divergence. Once the loss stabilizes, crank it up.
*. Do unto others’ hyperparameters as you would have them do unto yours. *. Do unto others’ hyperparameters as you would have them do unto yours.
*. “Innovative architecture” means never asking “did we implement a proper baseline?” *. “Innovative architecture” means never asking “did we implement a proper baseline?”
*. Only you can prevent vanishing gradients. *. Only you can prevent reward hacking.
*. Your model is in the leaderboards: be sure it has dropout. *. Your model is in the leaderboards: be sure it has dropout.
*. The longer training goes without overfitting, the bigger the validation-set disaster. *. The longer training goes without overfitting, the bigger the validation-set disaster.
*. If the optimizer is leading from the front, watch for exploding gradients in the rear. *. If the optimizer is leading from the front, watch for exploding gradients in the rear.