Artificial Neuron Network Implementation of Boolean Logic Gates by Perceptron and Threshold Element as Neuron Output Function

Threshold functions and Artificial Neural Networks (ANNs) are known for many years and have been thoroughly analyzed. The primary interest of these paper is to implement the basic logic gates of AND and EXOR by Artificial Neuron Network using Perceptron, and Threshold elements as Neuron output functions. The McCulloch-Pitts neural model was applied as linear threshold gate. The linear threshold gate was used to classify the set of inputs (1, 2) into two classes, which yielded a binary output,. The weighted values 1, 2, were normalized in the ranges of either (0, 1) or (-1, 1) and associated with each input line (1, 2), sum is the weighted sum, and T is a threshold constant. With the binary inputs of 1, 2 = 0 or 1, the weights 1, 2 = 1, and an offset -1.5, weighted summation as propagation, the output of the binary AND function unit was defined as = (-1.5 + 1 + 2), with () = 0 less than 0 and () = 1 0.