Analyzing the Energy Landscapes of Distributed Winner-Take-All Networks
Abstract
DCPS (the Distributed Connectionist Production System) is a neural network with complex dynamical properties. Visualizing the energy landscapes of some of its component modules leads to a better intuitive understanding of the model, and suggests ways in which its dynamics can be controlled in order to improve performance on difficult cases.
Cite
Text
Touretzky. "Analyzing the Energy Landscapes of Distributed Winner-Take-All Networks." Neural Information Processing Systems, 1988.Markdown
[Touretzky. "Analyzing the Energy Landscapes of Distributed Winner-Take-All Networks." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/touretzky1988neurips-analyzing/)BibTeX
@inproceedings{touretzky1988neurips-analyzing,
title = {{Analyzing the Energy Landscapes of Distributed Winner-Take-All Networks}},
author = {Touretzky, David S.},
booktitle = {Neural Information Processing Systems},
year = {1988},
pages = {626-633},
url = {https://mlanthology.org/neurips/1988/touretzky1988neurips-analyzing/}
}