Abstract
Artificial neural networks (ANN) are efficient optimization tools that have emerged to simulate the methods of human thinking. Applications of ANNs have been reported in areas such as control, telecommunications, remote sensing, pattern recognition, and manufacturing. They can be taught the formulas of polynomial image interpolation and their variants to carry them out. Concepts related to ANNs give enough details to provide some understanding of what can be accomplished with neural network models and how these models are developed for image interpolation. The purpose of a cell is to receive information from other cells. Any cell between the input layer and the output layer is said to be in a hidden layer. During supervised training, every problem presented to a neural network is accompanied with an expected response. Unsupervised learning allows a neural network to extract useful information only from the redundancy of the patterns that are presented to it.