The most interesting feature of neural networks is their functionality to familiarize with challenges by means of exercise and, after sufficient training, to have the capacity to solve unfamiliar problems of the equal class. This method is referred to as generalization.

Learning is a developed term. A learning system changes itself in order to adapt to e.g. environmental changes. A neural network could learn from many things but, of course, there will always be the doubt of how you can implement it.