Numerical Integration Study Based on Triangle Basis Neural Network Algorithm

A new appproach to solve numerical integration is developsed in this paper, based on the algorithm of neural networks with triangle basis functions. The convergence theorem of the neural networks algorithm and the theorem of numerical integration solution and its inferences are presented and proved. By the examples of numerical integration the comparison is carried out with tradional methods. The results show that the numerical integration approach has the characteristics such as high precision, strong adaptablity, and the intergration of unknown fountions can be solved. Therefore, the numerical integration approach values significantly in many engineering applications, such as electronics, etc.