Abstract
Recurrent neural networks and exceedingly Long short-term memory (LSTM) have been investigated intensively in recent years due to their ability to model and predict nonlinear time-variant system dynamics. The present paper delivers a comprehensive overviewof existing LSTM cell derivatives and network architectures for time series prediction. A categorization in LSTM with optimized cell state representations and LSTM with interacting cell states is proposed. The investigated approaches are evaluated againstdefined requirements being relevant for an accurate time series prediction.These include short-term and long-term memory behavior, the ability for multimodal and multi-step ahead predictions and the according error propagation.Sequence-to-sequencenetworks with partially conditioning outperform the other approaches, such as bidirectional or associative networks, and are best suited to fulfill therequirements.
Users
Please
log in to take part in the discussion (add own reviews or comments).
