the
∞
.ai
Search
/
Concepts
trail ·
0 nodes
Every concept
Uncertainty
8 concepts, 8 reviewed and merged.
Decisions
Selective Prediction
Give the model the option to say nothing.
verified
Detection
Out-of-Distribution Detection
Before trusting a prediction, ask whether the input is the kind of thing the model was trained on at all.
verified
Foundations
Aleatoric Uncertainty
The uncertainty that is in the data itself.
verified
Distribution Shift
The data a model meets in deployment is never quite the data it was trained on.
verified
Epistemic Uncertainty
The uncertainty that comes from not having seen enough.
verified
Methods
Bayesian Neural Network
Instead of one number per weight, keep a distribution over each.
verified
Conformal Prediction
Stop asking the model for a confident label and ask it for a set.
verified
Deep Ensemble
Train the same architecture five times from different random seeds and keep all five.
verified