Recurrent Self-Organizing Map (RSOM) is studied in three di erent time series prediction cases. RSOM is used to cluster the series into local data sets, for which corresponding lo...
Timo Koskela, Markus Varsta, Jukka Heikkonen, Kimm...
: A new supervised learning procedure for training RBF networks is proposed. It uses a pair of parallel running Kalman filters to sequentially update both the output weights and th...
Abstract— Prediction of natural gas consumption is an important element in gas load management aimed to better utilize the facilities of a gas distribution system. The major chal...
Neural Network approaches to time series prediction are briefly discussed, and the need to specify an appropriately sized input window identified. Relevant theoretical results fro...
Abstract—In this contribution, the application of fully connected recurrent neural networks (FCRNNs) is investigated in the context of narrowband channel prediction. Three differ...