Truncated-Newton Training Algorithm for Neurocomputational Viscoplastic Model

We present an estimate approach to compute the viscoplastic behavior of a polymeric composite under different thermomechanical approaches. This investagation incorporates computational neural network as the tool for determining the creep behaviour of the composite. We propose a new second-order learning algorithm for training the multilayer networks. Training in the neural network is generally specified as the minimization of an appropriate error function with respect to parameters of the network (weights and learning rates) corresponding to excitory and inhibitory connections. We propose here a technique for error minimization based on the use of the Truncated Newton (TN) large-scale unconstrained minimization technique. This technique offers a more sophisticated use the of the TN minimization for gradient information compared to simple steepest descent methods. The technique is used in the context of application to neural networks In this work we specify the necessary details for implementing the Truncated Newton methods for training of the neural networks, and provide comparative experimental results from use of these methods to depict the viscoplastic behavior of a polymeric composite. These results verify superiority of the present approach.