A Lagrangian Formulation for Optical Backpropagation Training in Kerr-Type Optical Networks
Abstract
A training method based on a form of continuous spatially distributed optical error back-propagation is presented for an all optical network composed of nondiscrete neurons and weighted interconnections. The all optical network is feed-forward and is composed of thin layers of a Kerr(cid:173) type self focusing/defocusing nonlinear optical material. The training method is derived from a Lagrangian formulation of the constrained minimization of the network error at the output. This leads to a formulation that describes training as a calculation of the distributed error of the optical signal at the output which is then reflected back through the device to assign a spatially distributed error to the internal layers. This error is then used to modify the internal weighting values. Results from several computer simulations of the training are presented, and a simple optical table demonstration of the network is discussed.
Cite
Text
Steck et al. "A Lagrangian Formulation for Optical Backpropagation Training in Kerr-Type Optical Networks." Neural Information Processing Systems, 1994.Markdown
[Steck et al. "A Lagrangian Formulation for Optical Backpropagation Training in Kerr-Type Optical Networks." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/steck1994neurips-lagrangian/)BibTeX
@inproceedings{steck1994neurips-lagrangian,
title = {{A Lagrangian Formulation for Optical Backpropagation Training in Kerr-Type Optical Networks}},
author = {Steck, James Edward and Skinner, Steven R. and Cruz-Cabrara, Alvaro A. and Behrman, Elizabeth C.},
booktitle = {Neural Information Processing Systems},
year = {1994},
pages = {771-778},
url = {https://mlanthology.org/neurips/1994/steck1994neurips-lagrangian/}
}