The process neural networks(PNNs) are networks that adapt to the process of signal input,whose elementary unit is the process neuron(PN),an emerging neuron model.

Its hidden layer and output layer are compose d of process neuron and the hidden layer function consists of wavelet function.

A continuous wavelet process neural networks(CWPNN)model is proposed based on wavelet analysis and process neural network theory in which the hidden layer is composed of process neurons and the hidden layer activation function is a wavelets function.

First the discrete data of both sample function and procedure neuron weight function is converted to spline function, and then spline function product integral of both samp.

The FPNN has three layers, and its hidden layer and output layer are procedure neuron.

The FPNN has three layers, and its hidden layer and output layer are composed of procedure neurons.

A process neural networks model and its application to dynamic forecasting;

Process neural networks with time-varying inputs and outputs and learning algorithm;

Aimed at the problems of the time-varying information processing and the dynamic system modeling, two kinds of process neural network models,including the rational formula process neural networks and the process neural networks with time-varying inputs and outputs function,were built in this paper.

Research and application of process neural network with two hidden-layer based on expansion of basis function;

A dynamic prediction method based on process neural networks is proposed for the process forecasting and prediction problem of dynamic system.

A modular process neural network model based on multi-basis-functions is brought forward in this article,in which the spatial aggregation and temporal limited accumulation of discrete-time inputs are involved.