I primarily want to know, if you have been given a quantity/feature and it's characteristics then how will you classify that feature? What's the intuitive criteria? From vision POV it becomes a bit easier but in general how will you understand them and put then in a right category or is it even a right question to ask in every domain of AI?
As a first step, take a look at the introduction chapter from this great review by one of the fathers of deep-learning.
For example, from page 9:
low-level visual features (like edge detectors) and intermediate-level visual features (like object parts)