Skip to Main Content
A new architecture based on wavelets and neural networks is proposed and implemented for learning a class of functions. The performance of such networks is analyzed for function learning. These functions belong to a common class but possess minor variations. The scheme developed makes use of wavelet neural network. It is useful to have a small dimensional network that can approximate a wide class of functions. The network has two levels of freedom. By this the network not only selects the parameters of the basis wavelets but also provides a variation in the choice.