AIExplainer

What is a translational invariance?

In an image classification problem, an algorithm's ability to successfully classify images even when the position of objects within the image changes.

In an image classification problem, an algorithm's ability to successfully classify images even when the position of objects within the image changes. For example, the algorithm can still identify a dog, whether it is in the center of the frame or at the left end of the frame. See also size invariance and rotational invariance.

Practitioners refer to translational invariance when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.