The filter is based on FIR Neural Net- work using Temporal Backpropagation.

The paper applied neural network to the research of wood drying control, established time-delay neural network schedule model useful to wood moisture content prediction, gave the identification structure of time-delay neural network and used practical drying data of three species to train and test the networks.

Based on the analysis of time-delay neural network and making use of the prior knowledge of character of discrete event dynamic system of military communication network, the uncertain time-delay neural network was put forward.

As a new data forecasting model,the double BP neural network combined model based on regressive neural network and time-delay neural network was proposed, which has the advantages of nonlinear combined forecasting methods.

By using the principle of various spatial curve classification and using time-delay neural network,the time-delay neural network can distinguishthe little circuit response difference caused by the soft fault and can classify the circuit response properly within the circuit part s tolerance,so the network can be used in diagnosis of the of analog circuitsoft fault.

The ability of neural networks to deal with time dynamic signal was improved with a new neural network architecture specializing in syllable recognition based on the time delay neural network (TDNN) and the convolutional neural network.