Input Augmentation

1. Input Augmentation

Input Augmentation artificially inflates training data size through applying expected transformations during training. This is a good regularizer against overfitting. Some transformations include:

Only transformations that can be expected in a real world case should be used.

2. Anomaly Detection

Anomaly Detection models identify unusual patterns that do not conform to expected behaviour. Input augmentation can help improve robustness by exposing the model to a wider variety of normal patterns during training. Can be:

Back to Home