Loading
Out-of-distribution detection flags an input that does not look like anything the model was trained on, so the model can refuse to predict instead of guessing; the Mahalanobis distance from the training cloud is the simplest such guard.
Anomaly detection identifies rare items that deviate significantly from the majority of the data (Wikipedia). The Mahalanobis distance measures how far a point lies from a distribution, accounting for its covariance (Wikipedia); computed in PCA space against the training cohort it gives a threshold beyond which a sample (a new platform, a different tissue, a corrupted file) is declared off-manifold and the prediction withheld. Passing the guard is necessary, not sufficient: an in-distribution sample can still yield an unstable prediction.
Shares Conformal prediction, Uncertainty quantification and confidence gates, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Domain shift and domain adaptation (cell line to patient), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Bootstrap resampling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Bootstrap resampling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Uncertainty quantification and confidence gates, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Domain shift and domain adaptation (cell line to patient), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Principal component analysis (PCA) as a feature compressor, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Principal component analysis (PCA) as a feature compressor, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.