Bifurcations of Recurrent Neural Networks in Gradient Descent Learning

@inproceedings{Doya1993BifurcationsOR,
  title={Bifurcations of Recurrent Neural Networks in Gradient Descent Learning},
  author={Kenji Doya},
  year={1993}
}
Asymptotic behavior of a recurrent neural network changes qualitatively at certain points in the parameter space, which are known as \bifurcation points". At bifurcation points, the output of a network can change discontinuously with the change of parameters and therefore convergence of gradient descent algorithms is not guaranteed. Furthermore, learning equations used for error gradient estimation can be unstable. However, some kinds of bifurcations are inevitable in training a recurrent… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 15 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 25 references