On stable learning of block-diagonal recurrent neural networks, Part 1: the RENNCOM algorithm

@article{Mastorocostas2004OnSL,
  title={On stable learning of block-diagonal recurrent neural networks, Part 1: the RENNCOM algorithm},
  author={P. A. Mastorocostas and J. B. Theocharis},
  journal={2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)},
  year={2004},
  volume={2},
  pages={815-820 vol.2}
}
A novel learning algorithm, the RENNCOM (recurrent neural network constrained optimization method), is suggested in this paper, for training block-diagonal recurrent neural networks. The training task is formulated as a constrained optimization problem, whose objective is twofold: (i) minimization of an error measure, leading to successful approximation of the input/output mapping and (ii) optimization of an additional functional, which aims at ensuring network stability throughout the learning… CONTINUE READING
6 Extracted Citations
5 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-5 of 5 references

J.I. StciI, “Local Srmetural Stability of Recurrent Networks with Time-Varying Weights,

  • NeurolNeworkr, vol
  • I.pp
  • 1999

Zisper, “A Learning Algorithm far Continually Running Fully Rccurrmt Neural Networks,

  • D. IO R.J. Williams
  • Neural Computation,
  • 1989

A Steepest - Ascent Method for Solving Optimum Programming hablcms Globally Asymptotical Stability of Discrete - Time Analog Neural Networks : IEEE Trans

  • Kams, S. Perantonis

Similar Papers

Loading similar papers…