<ul><li>An established failure mode for machine learning models occurs when the same features are equally likely to belong to class 0 and class 1.</li><li>Standard neural network architectures like MLPs or CNNs are not equipped to handle this problem.</li><li>A simple activation function called quantile activation (QACT) is proposed to address this issue.</li><li>QACT produces the relative quantile of the sample in its context distribution, improving generalization across distortions compared to conventional classifiers.</li></ul>

Quantile Activation: Correcting a Failure Mode of ML Models

Discover more