Highly Influenced

# Faster Learning for Dynamic Recurrent Backpropagation

@article{Fang1990FasterLF, title={Faster Learning for Dynamic Recurrent Backpropagation}, author={Yan Fang and Terrence J. Sejnowski}, journal={Neural Computation}, year={1990}, volume={2}, pages={270-273} }

- Published 1990 in Neural Computation
DOI:10.1162/neco.1990.2.3.270

The backpropagation learning algorithm for feedforward networks (Rumelhart et al. 1986) has recently been generalized to recurrent networks (Pineda 1989). The algorithm has been further generalized by Pearlmutter (1989) to recurrent networks that produce time-dependent trajectories. The latter method requires much more training time than the feedforward or static recurrent algorithms. Furthermore, the learning can be unstable and the asymptotic accuracy unacceptable for some problems. In this… CONTINUE READING

#### From This Paper

##### Figures, tables, and topics from this paper.

#### Citations

##### Publications citing this paper.

#### References

##### Publications referenced by this paper.

Showing 1-6 of 6 references