Wouldn’t your explainable rotated representation create a more robust model? Kind of like Newton’s model of gravity was a better model than Kepler and Copernicus computing nested ellipses. Your model might be immune to adversarial examples and might generalize outside of the training set.
Wouldn’t your explainable rotated representation create a more robust model? Kind of like Newton’s model of gravity was a better model than Kepler and Copernicus computing nested ellipses. Your model might be immune to adversarial examples and might generalize outside of the training set.