Learning in recurrent finite difference networks

@article{Tsung1995LearningIR,
  title={Learning in recurrent finite difference networks},
  author={Fu-Sheng Tsung and Garrison W. Cottrell},
  journal={International journal of neural systems},
  year={1995},
  volume={6 3},
  pages={249-56}
}
A recurrent learning algorithm based on a finite difference discretization of continuous equations for neural networks is derived. This algorithm has the simplicity of discrete algorithms while retaining some essential characteristics of the continuous equations. In discrete networks learning smooth oscillations is difficult if the period of oscillation is too large. The network either grossly distorts the waveforms or is unable to learn at all. We show how the finite difference formulation can… CONTINUE READING

From This Paper

Topics from this paper.

Similar Papers

Loading similar papers…