An adaptive training algorithm for layered perceptron type neural networks

Summary form only given, as follows. A training procedure that adapts the weights of a trained layered perceptron type artificial neural network to training data originating from a slowly varying nonstationary process has been proposed. The resulting adaptively trained neural network (ATNN), based on nonlinear programming techniques, was shown to adapt to new training data that are in conflict with earlier training data while affecting the neural networks´ response minimally to data elsewhere. When the ATNN is applied to the problem of electric load forecasting, it is shown to significantly outperform the conventionally trained layered perceptron