Construction of recurrent mixture models for time series classification

We present a new hierarchical network architecture that integrates the outputs of recurrent ANN. The purpose of this architecture is to apply decomposition of time-series learning tasks (using self-organization on multi-channel input). Our approach yields the variance-reducing benefits of techniques such as stacked generalization, but exploits the ability of abstract targets to be factored based upon preprocessing, feature extraction, or multimodal sensor constraints. This research demonstrates how prior information can be applied to learn factorial structure from time series, to build a mixture of recurrent ANN