Capacity and Information Efficiency of a Brain-like Associative Net
Abstract
We have determined the capacity and information efficiency of an associative net configured in a brain-like way with partial connec(cid:173) tivity and noisy input cues. Recall theory was used to calculate the capacity when pattern recall is achieved using a winners-take(cid:173) all strategy. Transforming the dendritic sum according to input activity and unit usage can greatly increase the capacity of the associative net under these conditions. For moderately sparse pat(cid:173) terns, maximum information efficiency is achieved with very low connectivity levels (~ 10%). This corresponds to the level of con(cid:173) nectivity commonly seen in the brain and invites speculation that the brain is connected in the most information efficient way.
Cite
Text
Graham and Willshaw. "Capacity and Information Efficiency of a Brain-like Associative Net." Neural Information Processing Systems, 1994.Markdown
[Graham and Willshaw. "Capacity and Information Efficiency of a Brain-like Associative Net." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/graham1994neurips-capacity/)BibTeX
@inproceedings{graham1994neurips-capacity,
title = {{Capacity and Information Efficiency of a Brain-like Associative Net}},
author = {Graham, Bruce and Willshaw, David},
booktitle = {Neural Information Processing Systems},
year = {1994},
pages = {513-520},
url = {https://mlanthology.org/neurips/1994/graham1994neurips-capacity/}
}