College of Science

A neural network has a parallel-distributed architecture with a large number of nodes and connection weights. The learning rule is one of the important attributes to specify for a neural network. It determines how to adapt connection weights in order to optimize the network performance. The Backpropagation network is the most well known and widely used among the current types of neural network systems available. It is a multilayer feedforward network with a powerful learning rule. The learning rule is known as Backpropagation.