Edit ‘the_seventy_maxims_of_maximally_effective_machine_learning_engineers’

the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco

@@ -7,10 +7,10 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
 *. 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 the accuracy is high enough, stakeholders will stop complaining about the compute costs.
-*. Harsh critiques have their place—usually in the rejected pull requests.
+*. Harsh critiques have their place – usually in the rejected pull requests.
 *. Never turn your back on a reinforcement learner.
 *. Sometimes the only way out is through… through another epoch.
-*. Every dataset is trainable—at least once.
+*. Every dataset is trainable at least once.
 *. 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.
 *. “Innovative architecture” means never asking “did we implement a proper baseline?”
@@ -69,4 +69,4 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
 *. If you can’t explain it, cite the arXiv paper.
 *. Deploying with confidence intervals doesn’t mean you shouldn’t also deploy with a kill switch.
 *. Sometimes SOTA is a function of who had the biggest TPU pod.
-*. Bugs are not an option—they are mandatory. The option is whether or not to catch them before releasing the paper.
+*. Bugs are not an option – they are mandatory. The option is whether or not to catch them before releasing the paper.