This paper addresses the problem of signal processing in neural network with linear units and includes an analysis of the representation of Boolean functions. ADALINE (Adaptive Linear Neuron or later Adaptive Linear Element) is a single layer neural network. It was developed by Bernard Widrow and Ted Hoff at Stanford University in 1960. It is based on the McCulloch–Pitts neuron and consists of a weight, a bias and a summation function. The difference between Adaline and the standard perceptron (McCulloch-Pitts) is that in the learning phase the weights are adjusted according to the weighted sum of the inputs. There also exists an extension of linear neural network known as Madaline. Learning is a process when free parameters (weights and bias levels) of a neural network are adapted and adjusted through a continuing process of stimulation by the environment in which the network is embedded. Generic computing units are split into two functional parts: an integration function reduces the arguments to a single value and the output or activation function produces the output of this node taking that single value as its argument.