Learning Abilities of Perceptrons:
Conversely computational learning theory is the study of what concepts particular learning schemes as representation and method detail as a famous example there is first highlighted in a very influential book by Minsky and Papert that involves perceptrons. Oftenly it has been mathematically proven in which the above method for learning perceptron weights will converge to a perfect classifier for learning tasks where the target concept is linearly separable.
Just to clearly understand what is and what isn't a linearly separable target function that we look atthe simplest functions of all and boolean functions. It means that these take two inputs that are either 1 or -1 and output either a 1 or a -1. So always notice that in other contexts there the values 0 and 1 are used instead of -1 and 1.