The Error Correction Learning with Delta Rule

Jogimol Joseph

Abstract: Learning rule is a method or a mathematical logic includes an iterative process that helps a Neural Network to learn from the existing conditions and improve its performance. In machine learning, the delta rule is a gradient descent learning rule for updating the weights of the inputs to artificial neurons in a single-layer neural network. It is a special case of the more general back propagation algorithm.

Keywords: Delta Rule, Back Propagation, Perceptron Error learning in ANN, Least Mean Square LMS Rule