On-line learning algorithms for locally recurrent neural networks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, methodology): “Popular algorithms used for training the RNN include the real time recurrent learning technique of [306], the causal recursive backpropagation algorithm of [307] and the backpropagation through time algorithm of [308], just to name a few.”
A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system (2010, methodology): “For prognostic tasks, the most promising methods are Recurrent Neural Networks (RNNs) [Campolucci et al., 1999] and Neuro-Fuzzy (NF) systems [Wang et al., 2004].”
Advanced Methods for Time Series Prediction Using Recurrent Neural Networks (2011, background): “They share the characteristic of having been initially elaborated for using the error gradient back-propagation of feed-forward neural networks (some of which have an adapted version today (Campolucci et al., 1999)).”