Polynomial Fitting Algorithm Based on Neural Network

As a method of function approximation, polynomial fitting has always been the main research hotspot in mathematical modeling. In many disciplines such as computer, physics, biology, neural networks have widely used, and most applications transformed into problems using networks. One reasons that can be used is it certain sense universal approximation. order to fit polynomial, this paper constructs three-layer feedforward network, uses Taylor series activation function, determines number hidden layer neurons according dimensions input variables. For explicit fitting, non-linear functions objective compares effects under different orders polynomials. implicit curves, current popular algorithms are compared analyzed. Experiments proved algorithm suitable for both fitting. The relatively simple, practical, easy calculate, efficiently achieve goal. At same time, computational complexity low, which application value.