This is the authors' abstract. We don't add key points for this paper.
A novel variant of the familiar backpropagation-through-time approach to training recurrent networks is described. This algorithm is intended to be used on arbitrary recurrent networks that run continually without ever being reset to an initial state, and it is specifically designed for computationally efficient computer implementation. This algorithm can be viewed as a cross between epochwise backpropagation through time, which is not appropriate for continually running networks, and the widely used on-line gradient approximation technique of truncated backpropagation through time.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Williams et al. (1990) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: