Evaluating models without test data (Practical AI #194)
Changelog Master Feed
Using Weight Watcher in the Training Loop?
Daniel: How does that change the workflow for someone who hasn't done what Daniel's done and gotten his hands on Weight Watcher? "Go back and look at the regularization. Did you, did you add enough drop outs on your layer?" he asks. He says maybe you need to run it longer. You need to run a SGD longer. Maybe you need to adjust some of your hyperparameters because you're not getting tuned. Try to adjust your hyperparameter so alpha goes down, not that it goes up"
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
