On the choice of parameters of the cost function in nested modular RNN's

@article{Mandic2000OnTC,
  title={On the choice of parameters of the cost function in nested modular RNN's},
  author={Danilo P. Mandic and Jonathon A. Chambers},
  journal={IEEE transactions on neural networks},
  year={2000},
  volume={11 2},
  pages={315-22}
}
We address the choice of the coefficients in the cost function of a modular nested recurrent neural-network (RNN) architecture, known as the pipelined recurrent neural network (PRNN). Such a network can cope with the problem of vanishing gradient, experienced in prediction with RNN's. Constraints on the coefficients of the cost function, in the form of a vector norm, are considered. Unlike the previous cost function for the PRNN, which included a forgetting factor motivated by the recursive… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 11 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 53 references

Relationship between the slope of the activation function and the learning rate for the RNN

  • D. P. Mandic, J. A. Chambers
  • eural Comput. , vol. 11, no. 5, pp. 1069–1077…
  • 1999
Highly Influential
9 Excerpts

Advanced PRNN based nonlinear prediction/system identification,”Dig

  • D. P. Mandic, J. A. Chambers
  • IEE Colloquium Nonlinear Signal Image Processing…
  • 1998
Highly Influential
5 Excerpts

Nonlinear prediction of speech with a pipelined recurrent neural network and advanced learning algorithms

  • D. P. Mandic, J. Baltersee, J. A. Chambers
  • inSignal Analysis and Prediction , A. Prochazka…
  • 1998
Highly Influential
6 Excerpts

Filter Theory

  • S. Haykin, Adaptive
  • 3rd ed. Englewood Cliffs, NJ: Prentice-Hall,
  • 1996
Highly Influential
5 Excerpts

Larimore, Theory and Design of Adaptive Filters

  • J. R. Treichler, C. R. Johnson, Jr., G M.
  • 1987
Highly Influential
4 Excerpts

Relationship between the slope of the activation function and the learning rate for the RNN , ” eural Comput

  • D. P. Mandic, J. A. Chambers
  • 1999

Similar Papers

Loading similar papers…