Local Feedback Multilayered Networks
Abstract
In this paper, we investigate the capabilities of local feedback multilayered networks, a particular class of recurrent networks, in which feedback connections are only allowed from neurons to themselves. In this class, learning can be accomplished by an algorithm that is local in both space and time. We describe the limits and properties of these networks and give some insights on their use for solving practical problems.
Cite
Text
Frasconi et al. "Local Feedback Multilayered Networks." Neural Computation, 1992. doi:10.1162/NECO.1992.4.1.120Markdown
[Frasconi et al. "Local Feedback Multilayered Networks." Neural Computation, 1992.](https://mlanthology.org/neco/1992/frasconi1992neco-local/) doi:10.1162/NECO.1992.4.1.120BibTeX
@article{frasconi1992neco-local,
title = {{Local Feedback Multilayered Networks}},
author = {Frasconi, Paolo and Gori, Marco and Soda, Giovanni},
journal = {Neural Computation},
year = {1992},
pages = {120-130},
doi = {10.1162/NECO.1992.4.1.120},
volume = {4},
url = {https://mlanthology.org/neco/1992/frasconi1992neco-local/}
}