Time series prediction using chaotic neural networks on the CATS benchmark

KIII is a strongly biologically inspired neural network model. It has a multi-layer architecture with excitatory and inhibitory neurons, which have massive lateral, feedforward, and delayed feedback connections between layers. KIII has been shown to be an efficient tool of classification and pattern recognition. In this work, we develop a methodology to use KIII for multi-step time series prediction. This method is applied to the IJCNN CATS benchmark data. Taking into account the results of CATS competition, we improve upon our method by tuning the K-network parameters, therefore providing a better set of parameters for prediction task.