Why you should care about debugging machine learning models
O'Reilly on Data
DECEMBER 12, 2019
Security vulnerabilities : adversarial actors can compromise the confidentiality, integrity, or availability of an ML model or the data associated with the model, creating a host of undesirable outcomes. For model training and selection, we recommend considering fairness metrics when selecting hyperparameters and decision cutoff thresholds.
Let's personalize your content