Abstract: Aiming at the training problem of process neural networks, a training algorithm based on numerical integralion was proposed. In proposed algorithm, the numerical integration was directly applied to deal with the weighted aggregation of dynamic samples and weight functions in time-domain,and the gradient descent method was used to adjust the weight function characteristic parameters and network property parameters. hhrec kinds of numerical integration methods of Trapezoidal, Simpson, and Cotes were designed. Taking the prediction of sunspot data as an example, the simulation results show that the training algorithms based on numerical integration arc efficient, and the approximation performance of Simpson integration is optimal.

Key words: Process neural networks, Learning algorithm, Numerical integration, Time-domain aggregation operation