Machines don’t learn. What a ’learning machine’ does, is find a mathematical formula, which when applied to a collection of inputs (the ’training data’), produces the desired output. This mathematical formula also generates the correct outputs for most other inputs (distinct from the training data) on the condition that those inputs come from the same or a similar statistical distribution as the one the training data was drawn from.

This isn’t learning because if you slightly distort the inputs, the output is very likely to become completely wrong. It’s not how learning in animals works.

Next -> What is Machine Learning