Topic
Generalisation and overfitting research, explained
3 open-access generalisation and overfitting studies, each with a flashcard deck and a quiz.
- Can one neural network score sleep across any clinic's data?
A single network trained on very diverse sleep recordings scored sleep about as well as the best of five human experts, even on datasets it never saw, without retraining.
- How much data do you need before ML predictions can be trusted?
With a few hundred users, cross-validation made models look much better than they really were, and even a useless model could often look good.
- Does a surgery-death prediction model work at other hospitals?
A lightweight gradient-boosted model using only routine lab values and basic surgical details predicted 30-day post-surgery death well and kept that accuracy when moved to other hospitals.