A Multi-dimension Predictor Based on ANN and Its Application

This paper presents a multi-dimension predictive model PDRNN based on the diagonal recurrent neural networks with a parallel learning algorithm. This model can be used to predict not only values, but also some points in the multi-dimension space. And also its applications in multi-dimension prediction will be discussed in the paper. Some analysis results show the significant improvement to multi parameters simultaneous prediction using the PDRNN algorithm.