Training Spatially Homogeneous Fully Recurrent Neural Networks in Eigenvalue Space

@article{Perfetti1997TrainingSH,
  title={Training Spatially Homogeneous Fully Recurrent Neural Networks in Eigenvalue Space},
  author={Renzo Perfetti and Emanuele Massarelli},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={1997},
  volume={10 1},
  pages={
          125-137
        }
}
A new design method for spatially-homogeneous, fully recurrent neural networks is presented. In our approach the eigenvalues of the synaptic matrix, rather than the weights, are learned from the examples. When the learning process is carried out, the connection weights are easily computed from the eigenvalues by inverse discrete Fourier transform. The adaptation is performed in the eigenvalue space in order to simply incorporate in the training algorithm the conditions for the uniqueness of the… CONTINUE READING