The Formation of Topographic Maps Which Maximize the Average Mutual Information of the Output Responses to Noiseless Input Signals
Abstract
This article introduces an extremely simple and local learning rule for to pographic map formation. The rule, called the maximum entropy learning rule (MER), maximizes the unconditional entropy of the map's output for any type of input distribution. The aim of this article is to show that MER is a viable strategy for building topographic maps that maximize the average mutual information of the output responses to noiseless input signals when only input noise and noise-added input signals are available.
Cite
Text
Van Hulle. "The Formation of Topographic Maps Which Maximize the Average Mutual Information of the Output Responses to Noiseless Input Signals." Neural Computation, 1997. doi:10.1162/NECO.1997.9.3.595Markdown
[Van Hulle. "The Formation of Topographic Maps Which Maximize the Average Mutual Information of the Output Responses to Noiseless Input Signals." Neural Computation, 1997.](https://mlanthology.org/neco/1997/hulle1997neco-formation/) doi:10.1162/NECO.1997.9.3.595BibTeX
@article{hulle1997neco-formation,
title = {{The Formation of Topographic Maps Which Maximize the Average Mutual Information of the Output Responses to Noiseless Input Signals}},
author = {Van Hulle, Marc M.},
journal = {Neural Computation},
year = {1997},
pages = {595-606},
doi = {10.1162/NECO.1997.9.3.595},
volume = {9},
url = {https://mlanthology.org/neco/1997/hulle1997neco-formation/}
}