Sign in

The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others

By Daniel Sikar and others
This study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering techniques to measure the distances between the predictions of a trained neural network and class centroids. By... Show more
July 10, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others
Click on play to start listening