Research Article
A Novel Single Neuron Perceptron with Universal Approximation and XOR Computation Properties
Algorithm 1
Proposed SNP algorithm.
Input: Initial random weights; and input bias b | (1) Take th learning sample (th and ) | | (3) Calculate the final output and error | | | (4) Update the weights by using excitatory rule | ; | | (5) Update the weights by using inhibitory rule | ; | | (6) If of training patterns then and proceed to the first | (7) Let epoch = epoch + 1 and | (8) If the stop criterion has not satisfied proceed to the first |
|