Faster Learning for Dynamic Recurrent Backpropagation

  title={Faster Learning for Dynamic Recurrent Backpropagation},
  author={Yan Fang and Terrence J. Sejnowski},
  journal={Neural Computation},
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.


Publications referenced by this paper.
Showing 1-6 of 6 references

Neural network analysis of distributed representations of sensorimotor transformations in the leech

  • S. R. Lockery, Y. Fang, T. J. Sejnowski
  • Neurai lnformafion Processing Systems 1989, D…
  • 1990
1 Excerpt

Similar Papers

Loading similar papers…