Convergence of BP algorithm for product unit neural networks with exponential weights

Product unit neural networks with exponential weights (PUNNs) can provide more powerful internal representation capability than traditional feed-forward neural networks. In this paper, a convergence result of the back-propagation (BP) algorithm for training PUNNs is presented. The monotonicity of the error function in the training iteration process is also guaranteed. A numerical example is given to support the theoretical findings.